https://github.com/kiranchhatre/amuse
공식 코드Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion
Papers with Code 아카이브
3D Shape Generation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 0
- 보존된 평가 기록
- 0
Image: Mo et al
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/kkakkkka/MambaTalk
공식 코드MambaTalk: Efficient Holistic Gesture Synthesis with Selective State Space Models
https://github.com/laughtervv/3DN
공식 코드https://github.com/liruihui/sp-gan
공식 코드https://github.com/liuzhengzhe/ISS-Image-as-Stepping-Stone-for-Text-Guided-3D-Shape-Generation
공식 코드ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation
https://github.com/liuzhengzhe/dreamstone-iss
공식 코드DreamStone: Image as Stepping Stone for Text-Guided 3D Shape Generation
https://github.com/liuzhengzhe/exim
공식 코드EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation
https://github.com/liuzhengzhe/towards-implicit-text-guided-shape-generation
공식 코드https://github.com/lorenmt/vsl
공식 코드https://github.com/mlvlab/DDMI
공식 코드https://github.com/mookerr/varges
공식 코드VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS
https://github.com/nagyrajmund/gesticulating_agent_unity
공식 코드A Framework for Integrating Gesture Generation Models into Interactive Conversational Agents
https://github.com/neuralcarver/michelangelo
공식 코드https://github.com/nv-tlabs/LION
공식 코드https://github.com/nv-tlabs/XCube
공식 코드XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies
https://github.com/octree-nn/octfusion
공식 코드OctFusion: Octree-based Diffusion Models for 3D Shape Generation
https://github.com/octree-nn/octgpt
공식 코드OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation
https://github.com/rowl1ng/3dsketch2shape
공식 코드https://github.com/shenhanqian/speechdrivestemplates
공식 코드Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates
https://github.com/sinhayan/surfnet
공식 코드SurfNet: Generating 3D shape surfaces using deep residual networks
https://github.com/tencent/flashvdm
공식 코드https://github.com/tencent/tencent-xr-3dgen
공식 코드Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation
https://github.com/teonikolov/genea_visualizer
공식 코드https://github.com/threestudio-project/threestudio
공식 코드https://github.com/ubisoft/ubisoft-laforge-ZeroEGGS
공식 코드ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech
https://github.com/xingqunqi-lab/emotiongestures
공식 코드EmotionGesture: Audio-Driven Diverse Emotional Co-Speech 3D Gesture Generation
https://github.com/yccyenchicheng/SDFusion
공식 코드SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation
https://github.com/yhw-yhw/talkshow
공식 코드https://github.com/youngseng/qpgesture
공식 코드https://github.com/youngseng/unifiedgesture
공식 코드UnifiedGesture: A Unified Gesture Synthesis Model for Multiple Skeletons
https://github.com/zhengxinyang/sdf-stylegan
공식 코드SDF-StyleGAN: Implicit SDF-Based StyleGAN for 3D Shape Generation
https://github.com/zyhbili/livelyspeaker
공식 코드LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation
https://github.com/ARISE-Initiative/robosuite
robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
https://github.com/CPUFronz/CapsVoxGAN
https://github.com/DiT-3D/DiT-3D
DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation
https://github.com/DreamTechAI/Direct3D
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.