https://github.com/nvidia-cosmos/cosmos-reason1
공식 코드Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning
Papers with Code 아카이브
3D Absolute Human Pose Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 4
- 평가표
- 3
- 보존된 평가 기록
- 6
This task aims to solve absolute (camera-centric not root-relative) 3D human pose estimation.
<span style="color:grey; opacity: 0.6">( Image credit: RootNet )</span>
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/open-debin/mm2latent
공식 코드MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance
https://github.com/open-mmlab/mmediting
공식 코드BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
https://github.com/picsart-ai-research/videoinr-continuous-space-time-super-resolution
공식 코드VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution
https://github.com/pixelite1201/agora_evaluation
공식 코드AGORA: Avatars in Geography Optimized for Regression Analysis
https://github.com/pku-yuangroup/envision3d
공식 코드https://github.com/pkunliu/isotropic3d
공식 코드Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding
https://github.com/proteus1991/RawVSR
공식 코드Exploit Camera Raw Data for Video Super-Resolution via Hidden Markov Model Inference
https://github.com/psyai-net/EmoTalk_release
공식 코드EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation
https://github.com/psyai-net/SelfTalk_release
공식 코드SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces
https://github.com/redrock303/revisiting-temporal-alignment-for-video-restoration
공식 코드https://github.com/researchmm/TTVSR
공식 코드Learning Trajectory-Aware Transformer for Video Super-Resolution
https://github.com/researchmm/ftvsr
공식 코드Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolution
https://github.com/researchmm/vqd-sr
공식 코드Learning Data-Driven Vector-Quantized Degradation Model for Animation Video Super-Resolution
https://github.com/rozumden/DeFMO
공식 코드https://github.com/rozumden/deblatting_python
공식 코드https://github.com/rozumden/fmo-deblurring-benchmark
공식 코드https://github.com/ruihangao/tactiledreamfusion
공식 코드Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
https://github.com/ryanxingql/winner-ntire22-vqe
공식 코드Progressive Training of A Two-Stage Framework for Video Restoration
https://github.com/shangwei5/st-avsr
공식 코드Arbitrary-Scale Video Super-Resolution with Structural and Textural Priors
https://github.com/shermanlian/swrn
공식 코드Sliding Window Recurrent Network for Efficient Video Super-Resolution
https://github.com/shivangi-aneja/FaceTalk
공식 코드FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models
https://github.com/sichun233746/motif
공식 코드https://github.com/sjtu-lucy/emoface
공식 코드https://github.com/ssfootball04/generative_pose
공식 코드Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking
https://github.com/stability-ai/generative-models
공식 코드Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models
https://github.com/subin-kim-cv/NVP
공식 코드Scalable Neural Video Representations with Learnable Positional Features
https://github.com/suyz526/zebrapose
공식 코드ZebraPose: Coarse to Fine Surface Encoding for 6DoF Object Pose Estimation
https://github.com/syguan96/dynaboa
공식 코드Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation
https://github.com/tang1705/seeclear-neurips24
공식 코드SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
https://github.com/tencentarc/animesr
공식 코드AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos
https://github.com/tencentarc/fastrealvsr
공식 코드Mitigating Artifacts in Real-World Video Super-Resolution Models
https://github.com/tencentarc/instantmesh
공식 코드https://github.com/thunil/TecoGAN
공식 코드Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation
https://github.com/tianyuan168326/SelfC
공식 코드https://github.com/tingtingliao/soap
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.