mlsanityData to 14 Oct 2026

SMPLX-Lite: A Realistic and Drivable Avatar Benchmark with Rich Geometry and Texture Annotations

arXiv 2405.19609 ↗First posted 30 May 2024cs.CV cs.GRcited by 7

Not on the map. Why?

Abstract (arXiv)

Recovering photorealistic and drivable full-body avatars is crucial for numerous applications, including virtual reality, 3D games, and tele-presence. Most methods, whether reconstruction or generation, require large numbers of human motion sequences and corresponding textured meshes. To easily learn a drivable avatar, a reasonable parametric body model with unified topology is paramount. However, existing human body datasets either have images or textured models and lack parametric models which fit clothes well. We propose a new parametric model SMPLX-Lite-D, which can fit detailed geometry of the scanned mesh while maintaining stable geometry in the face, hand and foot regions. We present SMPLX-Lite dataset, the most comprehensive clothing avatar dataset with multi-view RGB sequences, keypoints annotations, textured scanned meshes, and textured SMPLX-Lite-D models. With the SMPLX-Lite dataset, we train a conditional variational autoencoder model that takes human pose and facial keypoints as input, and generates a photorealistic drivable human avatar.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 26 of its 39 references that are in the map. First posted on arXiv 30 May 2024.

Builds on

26 of 39 references.

References · 26

  1. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  2. 2019Expressive Body Capture: 3D Hands, Face, and Body from a Single Imagecited by 1,612
  3. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,162
  4. 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
  5. 2019PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitizationcited by 818
  6. 2016Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Imagecited by 695
  7. 2020Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humanscited by 634
  8. 2019Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loopcited by 627
  9. 2020PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitizationcited by 521
  10. 2020Modular Primitives for High-Performance Differentiable Renderingcited by 441
  11. 2021Animatable Neural Radiance Fields for Modeling Dynamic Human Bodiescited by 361
  12. 2020ARCH: Animatable Reconstruction of Clothed Humanscited by 257
14 more
  1. 2021Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensorscited by 246
  2. 2021AGORA: Avatars in Geography Optimized for Regression Analysiscited by 205
  3. 2022Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlationcited by 197
  4. 2021SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networkscited by 181
  5. 2021ARCH++: Animation-Ready Clothed Human Reconstruction Revisitedcited by 174
  6. 2020Combining Implicit Function Learning and Parametric Models for 3D Human Reconstructioncited by 133
  7. 2022HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modelingcited by 117
  8. 2021Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Controlcited by 106
  9. 2017Detailed, accurate, human shape estimation from clothed 3D scan sequencescited by 89
  10. 2020SIZER: A Dataset and Model for Parsing 3D Clothing and Learning Size Sensitive 3D Clothingcited by 87
  11. 2021Driving-Signal Aware Full-Body Avatarscited by 81
  12. 2021Modeling Clothing as a Separate Layer for an Animatable Human Avatarcited by 66
  13. 2022PINA: Learning a Personalized Implicit Neural Avatar from a Single RGB-D Video Sequencecited by 46
  14. 2022Generalizable Neural Performer: Learning Robust Radiance Fields for Human Novel View Synthesiscited by 40

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 5; 2026: 2.

7 papers.

  1. 2025TaoAvatar: Real-Time Lifelike Full-Body Talking Avatars for Augmented Reality via 3D Gaussian Splattingcited by 11
  2. 2025BEAM: Bridging Physically-based Rendering and Gaussian Modeling for Relightable Volumetric Videocited by 5
  3. 2025HuMoCon: Concept Discovery for Human Motion Understandingcited by 4
  4. 2025Animating the Uncaptured: Humanoid Mesh Animation with Video Diffusion Modelscited by 3
  5. 2026ViHOI: Human-Object Interaction Synthesis with Visual Priorscited by 3
  6. 2025TriDiff-4D: Fast 4D Generation through Diffusion-based Triplane Re-posingcited by 1
  7. 2026UNICA: A Unified Neural Framework for Controllable 3D Avatarscited by 0