3D Human Reconstruction

Benchmarks archive 2025-07-28

10 leaderboard tables shown for this task, 10 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

15 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 59 papers with code (106 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• 3D Human Mesh Regression with Dense Correspondence
  10 Jun 2020 3 repositories listed Syntology ran 2 of 10 samples · 8 unverified
  This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i.
• PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization
  1 Apr 2020 3 repositories listed
  Although current approaches have demonstrated the potential in real world settings, they still fail to produce reconstructions with the level of detail often present in the input images.
• SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation
  29 Sep 2023 2 repositories listed
  1) For the data scaling, we perform a systematic investigation on 32 EHPS datasets, including a wide range of scenarios that a model trained on any single dataset cannot handle.
• AnthroNet: Conditional Generation of Humans via Anthropometrics
  7 Sep 2023 2 repositories listed
  We present a novel human body model formulated by an extensive set of anthropocentric measurements, which is capable of generating a wide range of human body shapes and poses.
• HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery
  12 Apr 2023 2 repositories listed Syntology ran 0 of 8 samples · 8 unverified
  To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework.
• SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
  27 Dec 2021 2 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as…
• ICON: Implicit Clothed humans Obtained from Normals
  16 Dec 2021 2 repositories listed
  First, ICON infers detailed clothed-human normals (front/back) conditioned on the SMPL(-X) normals.
• SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks
  7 Apr 2021 2 repositories listed Syntology ran 3 of 9 samples · 6 unverified · 9 pointer-only (licence)
  We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar.
• PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop
  30 Mar 2021 2 repositories listed
  Regression-based methods have recently shown promising results in reconstructing human meshes from monocular images.
• Nerfies: Deformable Neural Radiance Fields
  25 Nov 2020 2 repositories listed
  We present the first method capable of photorealistically reconstructing deformable scenes using photos/videos captured casually from mobile phones.
• Perceiving 3D Human-Object Spatial Arrangements from a Single Image in the Wild
  30 Jul 2020 2 repositories listed
  We present a method that infers spatial arrangements and shapes of humans and objects in a globally consistent 3D scene, all from a single image in-the-wild captured in an uncontrolled environment.
• LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
  13 Mar 2025 1 repository listed Syntology ran 0 of 1 samples · 1 unverified
  Animatable 3D human reconstruction from a single image is a challenging problem due to the ambiguity in decoupling geometry, appearance, and deformation.
• HumanGif: Single-View Human Diffusion with Generative Prior
  17 Feb 2025 1 repository listed
  While previous single-view-based 3D human reconstruction methods made significant progress in novel view synthesis, it remains a challenge to synthesize both view-consistent and pose-consistent results for animatable…
• Efficient Neural Implicit Representation for 3D Human Reconstruction
  23 Oct 2024 1 repository listed
  Our models achieve a training speed that is 110X faster than that of State-of-The-Art (SoTA) NeRF-based models.
• Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
  27 Sep 2024 1 repository listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  Compared to previous implicit-function-based methods, the point cloud diffusion model can capture the global consistent features to generate the occluded regions, and the denoising process corrects the misaligned SMPL…
• Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
  7 Apr 2024 1 repository listed Syntology ran 4 of 5 samples · 1 unverified · 5 pointer-only (licence)
  As a result, our CONTHO achieves state-of-the-art performance in both human-object contact estimation and joint reconstruction of 3D human and object.
• Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot
  22 Feb 2024 1 repository listed Syntology ran 8 of 9 samples · 1 unverified · 9 pointer-only (licence)
  We present Multi-HMR, a strong sigle-shot model for multi-person 3D human mesh recovery from a single RGB image.
• Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images
  6 Nov 2023 1 repository listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  The latest trends in the research field of single-view human reconstruction devote to learning deep implicit functions constrained by explicit body shape priors.
• SketchBodyNet: A Sketch-Driven Multi-faceted Decoder Network for 3D Human Reconstruction
  10 Oct 2023 1 repository listed
  Compared with natural images, freehand sketches are much more flexible to depict various shapes, providing a high potential and valuable way for 3D human reconstruction.
• One-Stage 3D Whole-Body Mesh Recovery with Component Aware Transformer
  28 Mar 2023 1 repository listed Syntology ran 3 of 3 samples · 0 unverified
  It is challenging to perform this task with a single network due to resolution issues, i.
• High-fidelity 3D Human Digitization from Single 2K Resolution Images
  27 Mar 2023 1 repository listed
  The low-resolution depth network predicts the global structure from a low-resolution image, and the part-wise image-to-normal network predicts the details of the 3D human body structure.
• SHERF: Generalizable Human NeRF from a Single Image
  22 Mar 2023 1 repository listed
  To this end, we propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding.
• X-Avatar: Expressive Human Avatars
  8 Mar 2023 1 repository listed
  Our method models bodies, hands, facial expressions and appearance in a holistic fashion and can be learned from either full 3D scans or RGB-D data.
• Vid2Avatar: 3D Avatar Reconstruction from Videos in the Wild via Self-supervised Scene Decomposition
  22 Feb 2023 1 repository listed Syntology ran 0 of 7 samples · 7 unverified
  Specifically, we define a temporally consistent human representation in canonical space and formulate a global optimization over the background model, the canonical human shape and texture, and per-frame human pose…
• MHEntropy: Entropy Meets Multiple Hypotheses for Pose and Shape Recovery
  1 Jan 2023 1 repository listed
  For monocular RGB-based 3D pose and shape estimation, multiple solutions are often feasible due to factors like occlusion and truncation.
• SEFD: Learning to Distill Complex Pose and Occlusion
  1 Jan 2023 1 repository listed
  This paper addresses the problem of three-dimensional (3D) human mesh estimation in complex poses and occluded situations.
• ECON: Explicit Clothed humans Optimized via Normal integration
  14 Dec 2022 1 repository listed
  To increase robustness for these cases, existing work uses an explicit parametric body model to constrain surface reconstruction, but this limits the recovery of free-form surfaces such as loose clothing that deviates…
• Super-resolution 3D Human Shape from a Single Low-Resolution Image
  23 Aug 2022 1 repository listed
  The approach overcomes limitations of existing approaches that reconstruct 3D human shape from a single image, which require high-resolution images together with auxiliary data such as surface normal or a parametric…
• Occupancy Planes for Single-view RGB-D Human Reconstruction
  4 Aug 2022 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  Specifically, a set of 3D locations within the view-frustum of the camera are first projected independently onto the image and a corresponding feature is subsequently extracted for each 3D location.
• AvatarGen: a 3D Generative Model for Animatable Human Avatars
  1 Aug 2022 1 repository listed
  Unsupervised generation of clothed virtual humans with various appearance and animatable poses is important for creating 3D human avatars and other AR/VR applications.

Syntology lines on 12 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.