报告论文安排

时间：2024年01月02日/09日 14:00-16:25

地点：高新校区 G2-B302

  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
1SA23168215/SA23168219/SA23168240/SC230020223. GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents
2SA23168224/SA23011229/SA23011276/SA232181774. BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
3SA23168180/SA23168182/SA23168185/SA2316819129. MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
4SA23218233/SA23229055/SA23229093/SL2221501057. 3D Gaussian Splatting for Real-Time Radiance Field Rendering
5SA23011155/SA23011059/SA2316819264. OctFormer: Octree-based Transformers for 3D Point Clouds
6SA23011156/SA23168251/SC2321904918. Film Grain Rendering and Parameter Estimation
7SA23168179/SA23168181/SA23168183/SA2316818455. GREIL-Crowds: Crowd Simulation with Deep Reinforcement Learning and Examples
8SA23011098/SA23011223/SA23168186/SA2322905463. Word-As-Image for Semantic Typography
9SA23218086/SA23011220/SA23218225/SA2301123473. Computational Design of LEGO® Sketch Art
10SA23011171/SA23011203/SA23011208/SA2322904199. Learning the Geodesic Embedding with Graph Neural Networks
1.9  
1SA23011036/SA23011052/SA23011096/SA230111958. The Visual Language of Fabrics
2BZ23011001/SA23218094/SA23218188/SA2321819349. UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
3BC23005018/SA23218199/SA23218200/SA2321820160. Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
4SA23218120/SA23218121/SA23218231/SA2322104371. Locally-Adaptive Level-of-Detail for Hardware-Accelerated Ray Tracing
5SA23011125/SA23011161/SA2301125131. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
6SA23011028/SA23011243/SA23229086/SA2322909269. HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion

SIGGRAPH 2023 papers: 70

TOG: Vol 42, No 4 (acm.org)

SIGGRAPH 2023 Papers (realtimerendering.com)

  1. Anatomically Detailed Simulation of Human Torso
  2. HACK: Learning a Parametric Head and Neck Model for High-fidelity Animation
  3. GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents
  4. BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer
  5. Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models
  6. Contact Edit: Artist Tools for Intuitive Modeling of Hand-Object Interactions
  7. ShapeCoder: Discovering Abstractions for Visual Programs from Unstructured Primitives
  8. The Visual Language of Fabrics
  9. ArrangementNet: Learning Scene Arrangements for Vectorized Indoor Scene Modeling
  10. Juxtaform: interactive visual summarization for exploratory shape design
  11. Patternshop: Editing Point Patterns by Image Manipulation
  12. VideoDoodles: Hand-Drawn Animations on Videos with Scene-Aware Canvases
  13. StripMaker: Perception-driven Learned Vector Sketch Consolidation
  14. Semi-supervised reference-based sketch extraction using a contrastive learning framework
  15. Rhizomorph: The Coordinated Function of Shoots and Roots
  16. Example-Based Procedural Modeling Using Graph Grammars
  17. Recursive Control Variates for Inverse Rendering
  18. Film Grain Rendering and Parameter Estimation
  19. Revisiting controlled mixture sampling for rendering applications
  20. Scratch-based Reflection Art via Differentiable Rendering
  21. Differential Operators on Sketches via Alpha Contours
  22. Min-Deviation-Flow in Bi-directed Graphs for T-Mesh Quantization
  23. Complex Wrinkle Field Evolution
  24. Sag-Free Initialization for Strand-Based Hybrid Hair Simulation
  25. CT2Hair: High-Fidelity 3D Hair Modeling using Computed Tomography
  26. Neural Prefiltering for Correlation-Aware Levels of Detail
  27. Beyond Chainmail: Computational Modeling of Discrete Interlocking Materials
  28. Random-Access Neural Compression of Material Textures
  29. MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis in Unbounded Scenes
  30. Locally Attentional SDF Diffusion for Controllable 3D Shape Generation
  31. 3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
  32. Composite Motion Learning with Task Control
  33. Example-based Motion Synthesis via Generative Motion Matching
  34. Learning Physically Simulated Tennis Skills from Broadcast Videos
  35. Image vectorization and editing via linear gradient layer decomposition
  36. ColorfulCurves: Palette-Aware Lightness Control and Color Editing via Sparse Optimization
  37. Guided Linear Upsampling
  38. Language-based Photo Color Adjustment for Graphic Designs
  39. Differentiable Stripe Patterns for Inverse Design of Structured Surfaces
  40. B-rep Matching for Collaborating Across CAD Systems
  41. Globally Consistent Normal Orientation for Point Clouds by Regularizing the Winding-Number Field
  42. Locally Meshable Frame Fields
  43. Neural Volumetric Reconstruction for Coherent Synthetic Aperture Sonar
  44. NeRO: Neural Geometry and BRDF Reconstruction of Reflective Objects from Multiview Images
  45. Surface Simplification using Intrinsic Error Metrics
  46. Robust Low-Poly Meshing for General 3D Models
  47. Evolutionary Piecewise Developable Approximations
  48. Micro-Mesh Construction
  49. UniTune: Text-Driven Image Editing by Fine Tuning a Diffusion Model on a Single Image
  50. Unsupervised Learning of Robust Spectral Shape Matching
  51. ETER: Elastic Tessellation for Real-Time Pixel-Accurate Rendering of Large-Scale NURBS Models
  52. Temporal Set Inversion for Animated Implicits
  53. Real-Time Radiance Fields for Single-Image Portrait View Synthesis
  54. Generating Activity Snippets by Learning Human-Scene Interactions
  55. GREIL-Crowds: Crowd Simulation with Deep Reinforcement Learning and Examples
  56. DreamFace: Progressive Generation of Animatable 3D Faces under Text Guidance
  57. 3D Gaussian Splatting for Real-Time Radiance Field Rendering
  58. Shortest Path to Boundary for Self-Intersecting Meshes
  59. P2M: A Fast Solver for Querying Distance from Point to Mesh Surface
  60. Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models
  61. Blended Latent Diffusion
  62. Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models
  63. Word-As-Image for Semantic Typography
  64. OctFormer: Octree-based Transformers for 3D Point Clouds
  65. Dictionary Fields: Learning a Neural Basis Decomposition
  66. ScanBot: Autonomous Reconstruction via Deep Reinforcement Learning
  67. AvatarReX: Real-time Expressive Full-body Avatars
  68. SketchFaceNeRF: Sketch-based Facial Generation and Editing in Neural Radiance Fields
  69. HumanRF: High-Fidelity Neural Radiance Fields for Humans in Motion
  70. NeRSemble: Multi-view Radiance Field Reconstruction of Human Heads

SIGGRAPH Asia 2023 papers: 55

TOG: Vol 42, No 6 (acm.org)

SIGGRAPH Asia 2023 Papers (realtimerendering.com)

  1. Locally-Adaptive Level-of-Detail for Hardware-Accelerated Ray Tracing
  2. Towards Garment Sewing Pattern Reconstruction from a Single Image
  3. Computational Design of LEGO® Sketch Art
  4. FLARE: Fast Learning of Animatable and Relightable Mesh Avatars
  5. SAILOR: Synergizing Radiance and Occupancy Fields for Live Human Performance Capture
  6. Neural Field Convolutions by Repeated Differentiation
  7. GANeRF: Leveraging Discriminators to Optimize Neural Radiance Fields
  8. CamP: Camera Preconditioning for Neural Radiance Fields
  9. An Unified λ-subdivision Scheme for Quadrilateral Meshes with Optimal Curvature Performance in Extraordinary Regions
  10. Topology Guaranteed B-Spline Surface/Surface Intersection
  11. Projective Sampling for Differentiable Rendering of Geometry
  12. Warped-Area Reparameterization of Differential Path Integrals
  13. Amortizing Samples in Physics-Based Inverse Rendering Using ReSTIR
  14. ReShader: View-Dependent Highlights for Single Image View-Synthesis
  15. Discontinuity-Aware 2D Neural Fields
  16. An Implicit Neural Representation for the Image Stack: Depth, All in Focus, and High Dynamic Range
  17. MetaLayer: A Meta-Learned BSDF Model for Layered Materials
  18. Controllable Group Choreography Using Contrastive Diffusion
  19. BakedAvatar: Baking Neural Fields for Real-Time Head Avatar Synthesis
  20. AvatarStudio: Text-Driven Editing of 3D Dynamic Human Head Avatars
  21. TwinTex: Geometry-Aware Texture Generation for Abstracted 3D Architectural Models
  22. EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation
  23. IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers
  24. DR-Occluder: Generating Occluders Using Differentiable Rendering
  25. Differentiable Rendering of Parametric Geometry
  26. Diffusion Posterior Illumination for Ambiguity-Aware Inverse Rendering
  27. Metric Optimization in Penner Coordinates
  28. Efficient Cone Singularity Construction for Conformal Parameterizations
  29. Learning the Geodesic Embedding with Graph Neural Networks
  30. Enhancing Diffusion Models with 3D Perspective Geometry Constraints
  31. Low-Light Image Enhancement with Wavelet-Based Diffusion Models
  32. Concept Decomposition for Visual Exploration and Inspiration
  33. GeoLatent: A Geometric Approach to Latent Space Design for Deformable Shape Generators
  34. A Neural Space-Time Representation for Text-to-Image Personalization
  35. ProSpect: Prompt Spectrum for Attribute-Aware Personalization of Diffusion Models
  36. Robust Zero Level-Set Extraction from Unsigned Distance Fields Based on Double Covering
  37. MIPS-Fusion: Multi-Implicit-Submaps for Scalable and Robust Online Neural RGB-D Reconstruction
  38. Fluid Simulation on Neural Flow Maps
  39. Interaction-Driven Active 3D Reconstruction with Object Interiors
  40. Online Scene CAD Recomposition via Autonomous Scanning
  41. Scene-Aware Activity Program Generation with Language Guidance
  42. From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans
  43. Variational Barycentric Coordinates
  44. Text-Guided Synthesis of Eulerian Cinemagraphs
  45. Adaptive Shells for Efficient Neural Radiance Field Rendering
  46. ScaNeRF: Scalable Bundle-Adjusting Neural Radiance Fields for Large-Scale Scene Rendering
  47. Decaf: Monocular Deformation Capture for Face and Hand Interactions
  48. Learning Based 2D Irregular Shape Packing
  49. Neural Packing: from Visual Sensing to Reinforcement Learning
  50. Reconstruction of Machine-Made Shapes from Bitmap Sketches
  51. EMS: 3D Eyebrow Modeling from Single-View Images
  52. GroomGen: A High-Quality Generative Hair Model Using Hierarchical Latent Representations
  53. Slippage-Preserving Reshaping of Human-Made 3D Content
  54. Reconstructing Close Human Interactions from Multiple Views
  55. Neural-Singular-Hessian: Implicit Neural Representation of Unoriented Point Clouds by Enforcing Singular Hessian