3D Object Reconstruction

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

4 leaderboard tables shown for this task, 4 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

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

Subtasks archive 2025-07-28

4 subtasks in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 73 papers with code (153 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-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction
  2 Apr 2016 13 repositories listed
  Inspired by the recent success of methods that employ shape priors to achieve robust 3D reconstructions, we propose a novel recurrent neural network architecture that we call the 3D Recurrent Reconstruction Neural…
• Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images
  31 Jan 2019 5 repositories listed Syntology ran 1 of 9 samples · 8 unverified
  Then, a context-aware fusion module is introduced to adaptively select high-quality reconstructions for each part (e.
• Pixel2Mesh: Generating 3D Mesh Models from Single RGB Images
  5 Apr 2018 5 repositories listed Syntology ran 1 of 12 samples · 11 unverified
  We propose an end-to-end deep learning architecture that produces a 3D shape in triangular mesh from a single color image.
• Grasping Field: Learning Implicit Representations for Human Grasps
  10 Aug 2020 4 repositories listed
  Specifically, our generative model is able to synthesize high-quality human grasps, given only on a 3D object point cloud.
• A Point Set Generation Network for 3D Object Reconstruction from a Single Image
  2 Dec 2016 4 repositories listed Syntology ran 2 of 6 samples · 4 unverified · 2 pointer-only (licence)
  Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
• Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images
  22 Jun 2020 3 repositories listed Syntology ran 2 of 6 samples · 4 unverified
  A multi-scale context-aware fusion module is then introduced to adaptively select high-quality reconstructions for different parts from all coarse 3D volumes to obtain a fused 3D volume.
• Matryoshka Networks: Predicting 3D Geometry via Nested Shape Layers
  29 Apr 2018 3 repositories listed
  We scale this baseline to higher resolutions by proposing a memory-efficient shape encoding, which recursively decomposes a 3D shape into nested shape layers, similar to the pieces of a Matryoshka doll.
• Multi-View Silhouette and Depth Decomposition for High Resolution 3D Object Representation
  27 Feb 2018 3 repositories listed
  We consider the problem of scaling deep generative shape models to high-resolution.
• Neural 3D Mesh Renderer
  20 Nov 2017 3 repositories listed
  Using this renderer, we perform single-image 3D mesh reconstruction with silhouette image supervision and our system outperforms the existing voxel-based approach.
• Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction
  21 Jun 2017 3 repositories listed
  Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones.
• 3D Object Reconstruction from Hand-Object Interactions
  3 Apr 2017 3 repositories listed
  Recent advances have enabled 3d object reconstruction approaches using a single off-the-shelf RGB-D camera.
• Refine3DNet: Scaling Precision in 3D Object Reconstruction from Multi-View RGB Images using Attention
  1 Dec 2024 2 repositories listed
  Generating 3D models from multi-view 2D RGB images has gained significant attention, extending the capabilities of technologies like Virtual Reality, Robotic Vision, and human-machine interaction.
• GaussianObject: High-Quality 3D Object Reconstruction from Four Views with Gaussian Splatting
  15 Feb 2024 2 repositories listed Syntology ran 7 of 11 samples · 4 unverified · 11 pointer-only (licence)
  Then we construct a Gaussian repair model based on diffusion models to supplement the omitted object information, where Gaussians are further refined.
• Share With Thy Neighbors: Single-View Reconstruction by Cross-Instance Consistency
  21 Apr 2022 2 repositories listed
  Approaches for single-view reconstruction typically rely on viewpoint annotations, silhouettes, the absence of background, multiple views of the same instance, a template shape, or symmetry.
• UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction
  20 Apr 2021 2 repositories listed Syntology ran 8 of 10 samples · 2 unverified
  At the same time, neural radiance fields have revolutionized novel view synthesis.
• 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.
• Deep Predictive Motion Tracking in Magnetic Resonance Imaging: Application to Fetal Imaging
  25 Sep 2019 2 repositories listed
  Nevertheless, visual monitoring of fetal motion based on displayed slices, and navigation at the level of stacks-of-slices is inefficient.
• Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning
  3 Apr 2019 2 repositories listed Syntology ran 1 of 11 samples · 10 unverified
  Rendering bridges the gap between 2D vision and 3D scenes by simulating the physical process of image formation.
• 3D Point Capsule Networks
  27 Dec 2018 2 repositories listed
  In this paper, we propose 3D point-capsule networks, an auto-encoder designed to process sparse 3D point clouds while preserving spatial arrangements of the input data.
• Dense 3D Object Reconstruction from a Single Depth View
  1 Feb 2018 2 repositories listed
  Unlike existing work which typically requires multiple views of the same object or class labels to recover the full 3D geometry, the proposed 3D-RecGAN++ only takes the voxel grid representation of a depth view of the…
• 3D Object Reconstruction from a Single Depth View with Adversarial Learning
  26 Aug 2017 2 repositories listed
  In this paper, we propose a novel 3D-RecGAN approach, which reconstructs the complete 3D structure of a given object from a single arbitrary depth view using generative adversarial networks.
• Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision
  1 Dec 2016 2 repositories listed
  We demonstrate the ability of the model in generating 3D volume from a single 2D image with three sets of experiments: (1) learning from single-class objects; (2) learning from multi-class objects and (3) testing on…
• HuSc3D: Human Sculpture dataset for 3D object reconstruction
  9 Jun 2025 1 repository listed
  3D scene reconstruction from 2D images is one of the most important tasks in computer graphics.
• Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention
  23 May 2025 1 repository listed Syntology ran 2 of 10 samples · 8 unverified
  Generating high-resolution 3D shapes using volumetric representations such as Signed Distance Functions (SDFs) presents substantial computational and memory challenges.
• Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction
  19 Feb 2025 1 repository listed Syntology ran 2 of 2 samples · 0 unverified · 2 pointer-only (licence)
  Recent advancements in implicit 3D reconstruction methods, e.
• View Transformation Robustness for Multi-View 3D Object Reconstruction with Reconstruction Error-Guided View Selection
  16 Dec 2024 1 repository listed
  To fully utilize the power of Stable Diffusion models without extra inference computation burdens, we propose to generate novel views with Stable Diffusion models for better view transformation robustness.
• LeanGaussian: Breaking Pixel or Point Cloud Correspondence in Modeling 3D Gaussians
  25 Apr 2024 1 repository listed
  In this paper, we introduce LeanGaussian, a novel approach that treats each query in deformable Transformer as one 3D Gaussian ellipsoid, breaking the pixel or point cloud correspondence constraints.
• 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.
• SUP-NeRF: A Streamlined Unification of Pose Estimation and NeRF for Monocular 3D Object Reconstruction
  23 Mar 2024 1 repository listed
  While gradient-based optimization in a NeRF framework updates the initial pose, this paper highlights that scale-depth ambiguity in monocular object reconstruction causes failures when the initial pose deviates…
• TripoSR: Fast 3D Object Reconstruction from a Single Image
  4 Mar 2024 1 repository listed Syntology ran 4 of 4 samples · 0 unverified
  This technical report introduces TripoSR, a 3D reconstruction model leveraging transformer architecture for fast feed-forward 3D generation, producing 3D mesh from a single image in under 0.

Syntology lines on 11 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.