报告论文安排

时间：2026年01月05日/12日 14:00-17:00

地点：高新校区 GT-A405

  1. 报告属于正常上课，所有同学不得无故缺席。
  2. 每篇论文报告总时长为12分钟左右，其中陈述不超过10分钟（包括展示video），提问2分钟左右，建议ppt不超过15页！
  3. 由于每篇论文的报告时间有限，比较短，因此报告的重点在于：简单介绍作者和单位情况； 主要讲一下这篇文章在做什么(What)？为什么做这个问题(motivation-Why)？这个问题以前有些什么工作？ 难点在哪里？这篇文章解决了什么样的难点或提出什么样的新方法(selling points)？局限和未来工作(limitation and future work)？ 细节若太多不用展开，关键要让大家知道这篇文章的主要思想和价值所在。
  4. 请大家尽量在网上去找关于你所负责报告论文的相关资料。如各个作者的主页，项目网页。 很多作者会把论文、video、甚至将PPT放在他的主页。讲解论文时，论文中的图片、视频均播放给大家看一下。 “一图胜千言”，视频又能胜于图片。
  5. 书面报告要求采用科研论文格式（标题、摘要、关键字、正文、参考文献等）撰写， 内容可以是所报告论文的概览、同主题多篇论文的综述等。
  6. 评分：PPT口头报告（小组） + 书面报告（个人）
序号学号论文
1.5Design/Rendering/Human 
1SA25168185/SA25168242/SA25168249/SA251683195. DesignManager: An Agent-Powered Copilot for Designers to Integrate AI Design Tools into Creative Workflows
2SA25168172/SA2516817710. Learning to Draw Is Learning to See: Analyzing Eye Tracking Patterns for Assisted Observational Drawing
3SA25011172/SA25011288/SA2516821547. WishGI: Lightweight Static Global Illumination Baking via Spherical Harmonics Fitting
4SA25221004/SA25229091/SA25229122125. High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
5SA25229077/SA252291067. AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
6SA25168189/SA25168264/SA25168277/SA2516829325. Facial Microscopic Structures Synthesis from a Single Unconstrained Image
7SA25218122/SA25218211/SA2522902050. Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models
8SA2501127151. Semantically Consistent Text-to-Motion with Unsupervised Styles
9SA25168224/SA25168282/SA25168296/SA25168297134. MyTimeMachine: Personalized Facial Age Transformation
10SA25168218/SA25168268/SA25168291/SA25218135149. Hand-Shadow Poser
11SA25168273/SA25168278/SA25168279/SA25168280158. Feeling Blue or Seeing Red? Investigating the effect of light color, shadow and realism on the perception of emotion of real and virtual humans
12SA23229077186. Constructing Diffusion Avatar with Learnable Embeddings
13SC25219043/SC25219053/SC25219054195. ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
1.12Image/Video/3D 
1BE23006020/BZ2422900181. PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models
2SA25011276/SA25168240/SA25168342/SA25219047118. IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting
3SA25168176/SA25168182/SA25168217/SA25168235197. DiffCamera: Arbitrary Refocusing on Images
4SA25168243/SA25168244/SA25168245199. Generating the Past, Present and Future from a Motion-Blurred Image
5SA25229023/SA25229048/SA25229081/SA2522908454. Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
6SA25218170/SA25218176/SA25218178/SA25218180244. VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
7SA25168223/SA25168239/SA25168257266. FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
8SA25168192/SA25168232/SA25168253/SA2516835832. Painting with 3D Gaussian Splat Brushes
9SA25011161/SA25218137/SA2501113867. Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
10BE24218011/BZ25229003/SA25011038/SA2516825491. FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Rendering
11SA25011016/SA25011051/SC2501102292. Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
12SA25011110/SA25168288/SA25218098/SA25218100126. Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting
13SA25168220274. Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion
14SA25218200287. ASIA: Adaptive 3D Segmentation using Few Image Annotations

 

SIGGRAPH 2025 papers: 160

TOG: Vol 44, No 4 (acm.org)

SIG'25 Proceedings

SIGGRAPH 2025 Papers (realtimerendering.com)

  1. AssetDropper: Asset Extraction via Diffusion Models with Reward-Driven Optimization
  2. MoVer: Motion Verification for Motion Graphics Animations
  3. EditDuet: A Multi-Agent System for Video Non-Linear Editing
  4. Order Matters: Learning Element Ordering for Graphic Design Generation
  5. DesignManager: An Agent-Powered Copilot for Designers to Integrate AI Design Tools into Creative Workflows
  6. Hybrid Tours: A Clip-based System for Authoring Long-take Touring Shots
  7. AutoKeyframe: Autoregressive Keyframe Generation for Human Motion Synthesis and Editing
  8. AnyTop: Character Animation Diffusion with Any Topology
  9. Hyper-Dimensional Deformation Simulation
  10. Learning to Draw Is Learning to See: Analyzing Eye Tracking Patterns for Assisted Observational Drawing
  11. Splat and Replace: 3D Reconstruction with Repetitive Elements
  12. SpotLessSplats: Ignoring Distractors in 3D Gaussian Splatting
  13. Radiance Surfaces: Optimizing Surface Representations with a 5D Radiance Field Loss
  14. Echoes of the Coliseum: Towards 3D Live streaming of Sports Events
  15. Revisiting Tradition and Beyond: A Customized Bilateral Filtering Framework for Point Cloud Denoising
  16. A Divide-and-Conquer Approach for Global Orientation of Non-Watertight Scene-Level Point Clouds Using 0-1 Integer Optimization
  17. Faraday Cage Estimation of Normals for Point Clouds and Ribbon Sketches
  18. A Polyhedral Construction of Empty Spheres in Discrete Distance Fields
  19. Variable Shared Template for Consistent Non-rigid ICP
  20. Facial Appearance Capture at Home with Patch-Level Reflectance Prior
  21. Text-based Animatable 3D Avatars with Morphable Model Alignment
  22. LAM: Large Avatar Model for One-shot Animatable Gaussian Head
  23. SOAP: Style-Omniscient Animatable Portraits
  24. 3DGH: 3D Head Generation with Composable Hair and Face
  25. Facial Microscopic Structures Synthesis from a Single Unconstrained Image
  26. NAM: Neural Adjoint Maps for refining shape correspondences
  27. GenAnalysis: Joint Shape Analysis by Learning Man-Made Shape Generators with Deformation Regularizations
  28. MASH: Masked Anchored SpHerical Distances for 3D Shape Representation and Generation
  29. Unsupervised Decomposition of 3D Shapes into Expressive and Editable Extruded Profile Primitives
  30. OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation
  31. BANG: Dividing 3D Assets via Generative Exploded Dynamics
  32. Painting with 3D Gaussian Splat Brushes
  33. FaceExpressions-70k: A Dataset of Perceived Expression Differences
  34. A Deep Learning-based Virtual Oculoplastic Surgery Simulator
  35. QUASAR: Quad-based Adaptive Streaming And Rendering
  36. VR-Doh: Hands-on 3D Modeling in Virtual Reality
  37. Discrete Torsion of Connection Forms on Simplicial Meshes
  38. Designing 3D Anisotropic Frame Fields with Odeco Tensors
  39. Piecewise Ruled Approximation for Freeform Mesh Surfaces
  40. Meschers: Geometry Processing of Impossible Objects
  41. Patch-Grid: An Efficient and Feature-Preserving Neural Implicit Surface Representation
  42. Variational Green and Biharmonic Coordinates for 2D Polynomial Cages
  43. Polynomial 2D Biharmonic Coordinates for High-order Cages
  44. Flexible 3D Cage-based Deformation via Green Coordinates on Bézier Patches
  45. CageNet: A Meta-Framework for Learning on Wild Meshes
  46. RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination
  47. WishGI: Lightweight Static Global Illumination Baking via Spherical Harmonics Fitting
  48. Gaussian Compression for Precomputed Indirect Illumination
  49. DuetGen: Music Driven Two-Person Dance Generation via Hierarchical Masked Modeling
  50. Motion-example-controlled Co-speech Gesture Generation Leveraging Large Language Models
  51. Semantically Consistent Text-to-Motion with Unsupervised Styles
  52. Sketch2Anim: Towards Transferring Sketch Storyboards into 3D Animation
  53. CineMaster: A 3D-Aware and Controllable Framework for Cinematic Text-to-Video Generation
  54. Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control
  55. Interspatial Attention for Efficient 4D Human Video Generation
  56. StableMakeup: When Real-World Makeup Transfer Meets Diffusion Model
  57. FashionComposer: Compositional Fashion Image Generation
  58. 3D Stylization via Large Reconstruction Model
  59. IMLS-Splatting: Efficient Mesh Reconstruction from Multi-view Images via Point Representation
  60. Spline Deformation Field
  61. Stochastic Preconditioning for Neural Field Optimization
  62. Variational Surface Reconstruction Using Natural Neighbors
  63. CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image
  64. CLR-Wire: Towards Continuous Latent Representations for 3D Curve Wireframe Generation
  65. PDT: Point Distribution Transformation with Diffusion Models
  66. RELATE3D: REfocusing Latent Adapter for Targeted local Enhancement and Editing in 3D Generation
  67. Drag Your Gaussian: Effective Drag-Based Editing with Score Distillation for 3D Gaussian Splatting
  68. CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation
  69. SwiftSketch: A Diffusion Model for Image-to-Vector Sketch Generation
  70. Aerial Path Online Planning for Urban Scene Updation
  71. Model See Model Do: Speech-Driven Facial Animation with Style Control
  72. Tiny is not small enough: High quality, low-resource facial animation models through hybrid knowledge distillation
  73. StreamME: Simplify 3D Gaussian Avatar within Live Stream
  74. ScaffoldAvatar: High-Fidelity Gaussian Avatars with Patch Expressions
  75. SqueezeMe: Mobile-Ready Distillation of Gaussian Full-Body Avatars
  76. Be Decisive: Noise-Induced Layouts for Multi-Subject Generation
  77. Cora: Correspondence-aware image editing using few step diffusion
  78. IntrinsicEdit: Precise generative image manipulation in intrinsic space
  79. 3D-Fixup: Advancing Photo Editing with 3D Priors
  80. MonetGPT: Solving Puzzles Enhances MLLMs' Image Retouching Skills
  81. PartEdit: Fine-Grained Image Editing using Pre-Trained Diffusion Models
  82. Instance Segmentation of Scene Sketches Using Natural Image Priors
  83. Instance Segmentation of Scene Sketches Using Natural Image Priors
  84. Power-Linear Polar Directional Fields
  85. NeurCross: A Neural Approach to Computing Cross Fields for Quad Mesh Generation
  86. Field Smoothness-Controlled Partition for Quadrangulation
  87. Feature-Aligned Parametrization in Penner Coordinates
  88. Rectangular Surface Parameterization
  89. Divide-and-Conquer Embedding
  90. 3DGS2: Near Second-order Converging 3D Gaussian Splatting
  91. FLoD: Integrating Flexible Level of Detail into 3D Gaussian Splatting for Customizable Rendering
  92. Virtualized 3D Gaussians: Flexible Cluster-based Level-of-Detail System for Real-Time Rendering of Composed Scenes
  93. Don't Splat your Gaussians: Volumetric Ray-Traced Primitives for Modeling and Rendering Scattering and Emissive Media
  94. When Gaussian Meets Surfel: Ultra-fast High-fidelity Radiance Field Rendering
  95. Deformable Beta Splatting
  96. Image-GS: Content-Adaptive Image Representation via 2D Gaussians
  97. BrepDiff: Single-Stage B-rep Diffusion Model
  98. Boolean Operation for CAD Models Using a Hybrid Representation
  99. PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction
  100. Stitch-A-Shape: Bottom-up Learning for B-Rep Generation
  101. DeFillet: Detection and Removal of Fillet Regions in Polygonal CAD Models
  102. HoLa: B-Rep Generation using a Holistic Latent Representation
  103. Physically Controllable Relighting of Photographs
  104. LightLab: Controlling Light Sources in Images with Diffusion Models
  105. GSHeadRelight: Fast Relightability for 3D Gaussian Head Synthesis
  106. RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets
  107. One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
  108. Anymate: A Dataset and Baselines for Learning 3D Object Rigging
  109. Splat4D: Diffusion-Enhanced 4D Gaussian Splatting for Temporally and Spatially Consistent Content Creation
  110. 4D Gaussian Videos with Motion Layering
  111. Photoreal Scene Reconstruction from an Egocentric Device
  112. On-the-fly Reconstruction for Large-Scale Novel View Synthesis from Unposed Images
  113. Monocular Online Reconstruction with Enhanced Detail Preservation
  114. TransparentGS: Fast Inverse Rendering of Transparent Objects with Gaussians
  115. pOps: Photo-Inspired Diffusion Operators
  116. Generating Past and Future in Digital Painting Processes
  117. InstanceGen: Image Generation with Instance-level Instructions
  118. IP-Prompter: Training-Free Theme-Specific Image Generation via Dynamic Visual Prompting
  119. PhysicsFC: Learning User-Controlled Skills for a Physics-Based Football Player Controller
  120. ViSA: Physics-based Virtual Stunt Actors for Ballistic Stunts
  121. Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control
  122. MaterialPicker: Multi-Modal DiT-Based Material Generation
  123. MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models
  124. A Fully-statistical Wave Scattering Model for Heterogeneous Surfaces
  125. High-Fidelity Novel View Synthesis via Splatting-Guided Diffusion
  126. Compensating Spatiotemporally Inconsistent Observations for Online Dynamic 3D Gaussian Splatting
  127. DAM-VSR: Disentanglement of Appearance and Motion for Video Super-Resolution
  128. DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
  129. Dynamic Mesh Processing on the GPU
  130. Sphere Carving: Bounding Volumes for Signed Distance Fields
  131. UltraMeshRenderer: Efficient Structure and Management of GPU Out-of-core Memory for Real-time Rendering of Gigantic 3D Meshes
  132. GAIA: Generative Animatable Interactive Avatars with Expression-conditioned Gaussians
  133. TeGA: Texture Space Gaussian Avatars for High-Resolution Dynamic Head Modeling
  134. MyTimeMachine: Personalized Facial Age Transformation
  135. InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention
  136. Relightable Full-Body Gaussian Codec Avatars
  137. EVA: Expressive Virtual Avatars from Multi-view Videos
  138. HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers
  139. Instant Self-Intersection Repair for 3D Meshes
  140. Feature-Preserving Mesh Repair via Restricted Power Diagram
  141. Topological Offsets
  142. Single Edge Collapse Quad-Dominant Mesh Reduction
  143. TetWeave: Isosurface Extraction using On-The-Fly Delaunay Tetrahedral Grids for Gradient-Based Mesh Optimization
  144. HexHex: Highspeed Extraction of Hexahedral Meshes
  145. VideoAnydoor: High-fidelity Video Object Insertion with Precise Motion Control
  146. Sketch3DVE: Sketch-based 3D-Aware Scene Video Editing
  147. ColorSurge: Bringing Vibrancy and Efficiency to Automatic Video Colorization via Dual-Branch Fusion
  148. Stressful Tree Modeling: Breaking Branches with Strands
  149. Hand-Shadow Poser
  150. DeepMill: Neural Accessibility Learning for Subtractive Manufacturing
  151. Towards Comprehensive Neural Materials: Dynamic Structure-Preserving Synthesis with Accurate Silhouette at Instant Inference Speed
  152. Generative Neural Materials
  153. Elevating 3D Models: High-Quality Texture and Geometry Refinement from a Low-Quality Model
  154. Putting Rigid Bodies to Rest
  155. A Versatile Quaternion-Based Constrained Rigid Body Dynamics
  156. C5D: Sequential Continuous Convex Collision Detection Using Cone Casting
  157. PaRas: A Rasterizer for Large-Scale Parametric Surfaces
  158. Feeling Blue or Seeing Red? Investigating the effect of light color, shadow and realism on the perception of emotion of real and virtual humans
  159. PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive transformer
  160. StructRe: Rewriting for Structured Shape Modeling

 

SIGGRAPH Asia 2025 papers: 156

TOG: Vol 44, No 6 (acm.org)

SIGA'25 Proceedings

SIGGRAPH Asia 2025 Papers (realtimerendering.com)

  1. RCTrans: Transparent Object Reconstruction in Natural Scene via Refractive Correspondence Estimation
  2. Topology-Aware Optimization of Gaussian Primitives for Human-Centric Volumetric Videos
  3. Surface-Aware Distilled 3D Semantic Features
  4. Lang3D-XL: Language Embedded 3D Gaussians for Large-scale Scenes
  5. PoissonNet: A Local-Global Approach for Learning on Surfaces
  6. Navigating with Annealing Guidance Scale in Diffusion Space
  7. Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation
  8. OmnimatteZero: Fast Training-free Omnimatte with Pre-trained Video Diffusion Models
  9. STGlight: Online Indoor Lighting Estimation via Spatio-Temporal Gaussian Fusion
  10. GenLit: Reformulating Single-Image Relighting as Video Generation
  11. DynVFX: Augmenting Real Videos with Dynamic Content
  12. Vertex Features for Neural Global Illumination
  13. Simplifying Textured Triangle Meshes in the Wild
  14. PartUV: Part-Based UV Unwrapping of 3D Meshes
  15. Solid-Shell Labeling for Discrete Surfaces
  16. RibbonSculpt: Voronoi Ball based 3D Sculpting from Sparse VR Ribbons
  17. Precise Gradient Discontinuities in Neural Fields for Subspace Physics
  18. Variational Neural Surfacing of 3D Sketches
  19. NeuVAS: Neural Implicit Surfaces for Variational Shape Modeling
  20. Neural Octahedral Field: Octahedral Prior for Simultaneous Smoothing and Sharp Edge Regularization
  21. Practical Gaussian Process Implicit Surfaces with Sparse Convolutions
  22. Generative Head-Mounted Camera Captures for Photorealistic Avatars
  23. InfiniHuman: Realistic 3D Human Creation with Precise Control
  24. HRM^2Avatar: High-Fidelity Real-Time Mobile Avatars from Monocular Phone Scans
  25. PriorAvatar: Efficient and Robust Avatar Creation from Monocular Video Using Learned Priors
  26. Constructing Diffusion Avatar with Learnable Embeddings
  27. Single-Image 3D Human Reconstruction with 3D-Aware Diffusion Priors and Facial Enhancement
  28. Neural Visibility of Point Sets
  29. PhySIC: Physically Plausible 3D Human-Scene Interaction and Contact from a Single Image
  30. CFC: Simulating Character-Fluid Coupling using a Two-Level World Model
  31. Lightweight, Edge-Aware, and Temporally Consistent Supersampling for Mobile Real-Time Rendering
  32. LSF-Animation: Label-Free Speech-Driven Facial Animation via Implicit Feature Representation
  33. High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
  34. Audio Driven Universal Gaussian Head Avatars
  35. ARTalk: Speech-Driven 3D Head Animation via Autoregressive Model
  36. X-Actor: Emotional and Expressive Long-Range Portrait Acting from Audio
  37. DiffCamera: Arbitrary Refocusing on Images
  38. Learning to Refocus with Video Diffusion Models
  39. Generating the Past, Present and Future from a Motion-Blurred Image
  40. UltraZoom: Generating Gigapixel Images from Regular Photos
  41. ShapeGen: Towards High-Quality 3D Shape Synthesis
  42. Autoregressive Generation of Static and Growing Trees
  43. OmniPart: Part-Aware 3D Generation with Semantic Decoupling and Structural Cohesion
  44. ART-DECO: Arbitrary Text Guidance for 3D Detailizer Construction
  45. SPGen: Spherical Projection as Consistent and Flexible Representation for Single Image 3D Shape Generation
  46. HRC-Net: Learning Visual Hypothesis, Representative, and Collaboration for Multi-Domain Image Inpainting
  47. Harnessing Diffusion-Yielded Score Priors for Image Restoration
  48. ELAD: Blind Face Restoration using Expectation-based Likelihood Approximation and Diffusion Prior
  49. Differentiable Light Transport with Gaussian Surfels via Adapted Radiosity for Efficient Relighting and Geometry Reconstruction
  50. Efficient Object Reconstruction with Differentiable Area Light Shading
  51. EGG-Fusion: Efficient 3D Reconstruction with Geometry-aware Gaussian Surfel on the Fly
  52. Inverse Radiative Transport for Infrared Scenes with Gaussian Primitives
  53. GigaSLAM: Large-Scale Monocular SLAM with Hierarchical Gaussian Splats
  54. WATER: Watertight Tessellation for Real-Time Pixel-Accurate Rendering of Large-Scale Surfaces
  55. TrackerSplat: Exploiting Point Tracking for Fast and Robust Dynamic 3D Gaussians Reconstruction
  56. Clustered Error Correction with Grouped 4D Gaussian Splatting
  57. Anchored 4D Gaussian Splatting for Dynamic Novel View Synthesis
  58. Prior-Enhanced Gaussian Splatting for Dynamic Scene Reconstruction from Casual Video
  59. 4DSloMo: 4D Reconstruction for High Speed Scene with Asynchronous Capture
  60. Split4D: Decomposed 4D Scene Reconstruction Without Video Segmentation
  61. Gaussian See, Gaussian Do: Semantic 3D Motion Transfer from Multiview Video
  62. Low-Rank Adaptation of Neural Fields
  63. Spectral Prefiltering of Neural Fields
  64. Marching Neurons: Accurate Surface Extraction for Neural Implicit Shapes
  65. SOF: Sorted Opacity Fields for Fast Unbounded Surface Reconstruction
  66. MILo: Mesh-In-the-Loop Gaussian Splatting for Detailed and Efficient Surface Reconstruction
  67. RaRa Clipper: A Clipper for Gaussian Splatting Based on Ray Tracer and Rasterizer
  68. Neural Image abstraction using long smoothing B-splines
  69. AutoBrep : Autoregressive B-Rep Generation with Unified Topology and Geometry
  70. BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch
  71. NURBS-Based Grid Shell Form Finding on Domains with Topologically Arbitrary Boundaries
  72. Overlap Region Extraction of Two NURBS Surfaces
  73. G2 Interpolating Spline with Local Maximum Curvature
  74. Img2CAD: Reverse Engineering 3D CAD Models from Images through VLM-Assisted Conditional Factorization
  75. Discovering Folding Lines for Surface Compression
  76. Closed-Form Construction of Voronoi Diagrams with Star-Shaped Metrics
  77. Object-level Visual Prompts for Compositional Image Generation
  78. ComposeMe: Attribute-Specific Image Prompts for Controllable Human Image Generation
  79. PartComposer: Learning and Composing Part-Level Concepts from Single-Image Examples
  80. AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swapping
  81. MALeR: Improving Compositional Fidelity in Layout-Guided Generation
  82. 3DPR: Single Image 3D Portrait Relighting with Generative Priors
  83. PhysiOpt: Physics-Driven Shape Optimization for 3D Generative Models
  84. VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
  85. SS4D: Native 4D Generative Model via Structured Spacetime Latents
  86. Generating 360° Video is What You Need For a 3D Scene
  87. PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion
  88. WorldExplorer: Towards Generating Fully Navigable 3D Scenes
  89. Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation
  90. CrossGen: Learning and Generating Cross Fields for Quad Meshing
  91. Lifted Surfacing of Generalized Sweep Volumes
  92. PAD3R: Pose-Aware Dynamic 3D Reconstruction from Casual Videos
  93. Detail Enhanced Gaussian Splatting for Large-Scale Volumetric Capture
  94. GS-RoadPatching: Inpainting Gaussians via 3D Searching and Placing for Driving Scenes
  95. Neural Hamiltonian Deformation Fields for Dynamic Scene Rendering
  96. MVP4D: Multi-View Portrait Video Diffusion for Animatable 4D Avatars
  97. MV-Performer: Taming Video Diffusion Model for Faithful and Synchronized Multi-view Performer Synthesis
  98. AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting
  99. Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images
  100. MODepth: Benchmarking Mobile Multi-frame Monocular Depth Estimation with Optical Image Stabilization
  101. From Rigging to Waving: 3D-Guided Diffusion for Natural Animation of Hand-Drawn Characters
  102. Sketch2PoseNet: Efficient and Generalized Sketch to 3D Human Pose Prediction
  103. AnimaX: Animating the Inanimate in 3D with Joint Video-Pose Diffusion Models
  104. Animus3D: Text-driven 3D Animation via Motion Score Distillation
  105. X-UniMotion: Animating Human Images with Expressive, Unified and Identity-Agnostic Motion Latents
  106. FairyGen: Storied Cartoon Video from a Single Child-Drawn Character
  107. 3D SMoE Splatting for Edge-aware Realtime Radiance Field Rendering
  108. AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views
  109. PowerGS: Display-Rendering Power Co-Optimization for Neural Rendering in Power-Constrained XR Systems
  110. Imaginarium: Vision-guided High-Quality 3D Scene Layout Generation
  111. Procedural Scene Programs for Open-Universe Scene Generation: LLM-Free Error Correction via Program Search
  112. Hierarchical Neural Semantic Representation for 3D Semantic Correspondence
  113. StyleSculptor: Zero-Shot Style-Controllable 3D Asset Generation with Texture-Geometry Dual Guidance
  114. Fuse3D: Generating 3D Assets Controlled by Multi-Image Fusion
  115. In-2-4D: Inbetweening from Two Single-View Images to 4D Generation
  116. FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion
  117. Generating Objects with Part-Articulation from a Single Image
  118. LARM: A Large Articulated Object Reconstruction Model
  119. ArtiLatent: Realistic Articulated 3D Object Generation via Structured Latents
  120. Assembler: Scalable 3D Part Assembly via Anchor Point Diffusion
  121. LLM-Primitives: Large Language Model for 3D Reconstruction with Primitives
  122. ConsiStyle: Style Diversity in Training-Free Consistent T2I Generation
  123. Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models
  124. PractiLight: Practical Light Control Using Foundational Diffusion Models
  125. Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA
  126. RL-ACD: Reinforcement Learning-based Approximate Convex Decomposition
  127. ASIA: Adaptive 3D Segmentation using Few Image Annotations
  128. Light-SQ: Structure-aware Shape Abstraction with Superquadrics for Generated Meshes
  129. MATStruct: High-quality Medial Mesh Computation via Structure-aware Variational Optimization
  130. Temporally Smooth Mesh Extraction for Procedural Scenes with Long-Range Camera Trajectories using Spacetime Octrees
  131. Design for Descent: What Makes a Shape Grammar Easy to Optimize?
  132. One-shot Embroidery Customization via Contrastive LoRA Modulation
  133. Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Volumetric Performance Captures
  134. Proteus-ID: ID-Consistent and Motion-Coherent Video Customization
  135. DreamID: High-Fidelity and Fast diffusion-based Face Swapping via Triplet ID Group Learning
  136. HiWave: Training-Free High-Resolution Image Generation via Wavelet-Based Diffusion Sampling
  137. Gradient-Weighted Feature Back-Projection: A Fast Alternative to Feature Distillation in 3D Gaussian Splatting
  138. Rigidity-Aware 3D Gaussian Deformation from a Single Image
  139. Neural Texture Splatting: Expressive 3D Gaussian Splatting for View Synthesis, Geometry, and Dynamic Reconstruction
  140. JumpingGS: Level-jump 3D Gaussian Representation for Delicate Textures in Aerial Large-scale Scene Rendering
  141. TC-GS: A Faster Gaussian Splatting Module Utilizing Tensor Cores
  142. DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting
  143. Closed-form Cauchy Coordinates and Their Derivatives for 2D High-order Cages
  144. Aerial Path Planning for Urban Geometry and Texture Co-Capture
  145. Compact shape representation utilizing local surface similarities
  146. In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation
  147. BlobCtrl: Taming Controllable Blob for Element-level Image Editing
  148. ConsistEdit: Highly Consistent and Precise Training-free Visual Editing
  149. Voost: A Unified and Scalable Diffusion Transformer for Bidirectional Virtual Try-On and Try-Off
  150. DreamO: A Unified Framework for Image Customization
  151. The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
  152. LVT: Large-Scale Scene Reconstruction via Local View Transformers
  153. CityGo: Lightweight Urban Modeling and Rendering with Proxy Buildings and Residual Gaussians
  154. GSWT: Gaussian Splatting Wang Tiles
  155. Spectral-GS: Taming 3D Gaussian Splatting with Spectral Entropy
  156. Editable Physically-based Reflections in Raytraced Gaussian Radiance Fields