R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow diffusion.
hub Canonical reference
TripoSR: Fast 3D Object Reconstruction from a Single Image
Canonical reference. 78% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
78% of classified citations
abstract
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 0.5 seconds. Building upon the LRM network architecture, TripoSR integrates substantial improvements in data processing, model design, and training techniques. Evaluations on public datasets show that TripoSR exhibits superior performance, both quantitatively and qualitatively, compared to other open-source alternatives. Released under the MIT license, TripoSR is intended to empower researchers, developers, and creatives with the latest advancements in 3D generative AI.
hub tools
citation-role summary
background 8
baseline 1
citation-polarity summary
representative citing papers
Img2CADSeq generates standard CAD sequences from images via a multi-stage pipeline with three-level hierarchical codebook encoding, importance-guided compression, and contrastive point-cloud conditioning of a VQ-Diffusion model, outperforming prior methods on new CAD-220K and PrintCAD datasets.
A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
AniGen directly generates animatable 3D assets with consistent shape, skeleton, and skinning from single images using unified S^3 fields and a two-stage flow-matching pipeline.
ContrAR benchmark reveals that current VLMs show reasonable understanding of contradictory virtual content in AR but need improvement in detection, reasoning, and balancing accuracy with latency.
CARI4D is the first category-agnostic pipeline that produces metric-scale, spatially and temporally consistent 4D reconstructions of human-object interactions from monocular RGB videos via foundation-model hypothesis selection, render-and-compare refinement, and contact reasoning.
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
PanoWorld autoregressively generates consistent multi-room 360-degree panoramas for whole-house VR using a floorplan-derived 3D shell as geometric proxy and a dynamic 3DGS cache for spatial memory.
Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.
VISER is a new visually realistic simulation benchmark for robot manipulation tasks that uses PBR materials and MLLM-assisted asset generation, achieving 0.92 Pearson correlation with real-world policy performance.
A generative-AI pipeline dynamically generates and anchors virtual assets to match the shape of physical props, enabling adaptive passive haptics in MR that users rate higher in realism, immersion, and enjoyment than static baselines.
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
A pipeline using SAM segmentation and Hi3DGen mesh generation, evaluated on 69 medieval figures, produces usable 3D models for XR and tactile applications with Hi3DGen as the best starting point.
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
InstantMesh produces diverse, high-quality 3D meshes from single images in seconds by combining a multi-view diffusion model with a sparse-view large reconstruction model and optimizing directly on meshes.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
AmaraSpatial-10K supplies 10K deployment-ready 3D assets with metric scaling and metadata, delivering 3.4x higher CLIP Recall@5 than Objaverse and 99.1% physics stability in Habitat-Sim.
UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.
FunCanon introduces functional object canonicalization with VLM affordances to create pose-aware action primitives for generalizable imitation learning in robotic manipulation.
citing papers explorer
-
R-DMesh: Video-Guided 3D Animation via Rectified Dynamic Mesh Flow
R-DMesh generates high-fidelity 4D meshes aligned to video by disentangling base mesh, motion, and a learned rectification jump offset inside a VAE, then using Triflow Attention and rectified-flow diffusion.
-
Img2CADSeq: Image-to-CAD Generation via Sequence-Based Diffusion
Img2CADSeq generates standard CAD sequences from images via a multi-stage pipeline with three-level hierarchical codebook encoding, importance-guided compression, and contrastive point-cloud conditioning of a VQ-Diffusion model, outperforming prior methods on new CAD-220K and PrintCAD datasets.
-
Towards Realistic and Consistent Orbital Video Generation via 3D Foundation Priors
A video generation approach conditions a base model with multi-scale 3D latent features and a cross-attention adapter to produce geometrically realistic and consistent orbital videos from one image.
-
AniGen: Unified $S^3$ Fields for Animatable 3D Asset Generation
AniGen directly generates animatable 3D assets with consistent shape, skeleton, and skinning from single images using unified S^3 fields and a two-stage flow-matching pipeline.
-
Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality
ContrAR benchmark reveals that current VLMs show reasonable understanding of contradictory virtual content in AR but need improvement in detection, reasoning, and balancing accuracy with latency.
-
CARI4D: Category Agnostic 4D Reconstruction of Human-Object Interaction
CARI4D is the first category-agnostic pipeline that produces metric-scale, spatially and temporally consistent 4D reconstructions of human-object interactions from monocular RGB videos via foundation-model hypothesis selection, render-and-compare refinement, and contact reasoning.
-
SVG360: Editable Multiview Vector Graphics from a Single SVG
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
-
Structured 3D Latents for Scalable and Versatile 3D Generation
SLAT provides a unified 3D latent representation enabling versatile high-quality generation across multiple output formats from text or image inputs.
-
GeoFlow: Enforcing Implicit Geometric Consistency in Video Generation
GeoFlow adds a geometry-consistency reward based on rigid camera flow and object appearance preservation, integrated via reinforcement fine-tuning to improve geometric coherence in video generation.
-
PanoWorld: A Generative Spatial World Model for Consistent Whole-House Panorama Synthesis
PanoWorld autoregressively generates consistent multi-room 360-degree panoramas for whole-house VR using a floorplan-derived 3D shell as geometric proxy and a dynamic 3DGS cache for spatial memory.
-
Sat3DGen: Comprehensive Street-Level 3D Scene Generation from Single Satellite Image
Sat3DGen improves geometric RMSE from 6.76m to 5.20m and FID from ~40 to 19 for street-level 3D generation from satellite images via geometry-centric constraints and perspective training.
-
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation
VISER is a new visually realistic simulation benchmark for robot manipulation tasks that uses PBR materials and MLLM-assisted asset generation, achieving 0.92 Pearson correlation with real-world policy performance.
-
Prop-Chromeleon: Adaptive Haptic Props in Mixed Reality through Generative Artificial Intelligence
A generative-AI pipeline dynamically generates and anchors virtual assets to match the shape of physical props, enabling adaptive passive haptics in MR that users rate higher in realism, immersion, and enjoyment than static baselines.
-
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective
The paper proposes a problem-driven taxonomy for feed-forward 3D scene modeling that groups methods by five core challenges: feature enhancement, geometry awareness, model efficiency, augmentation strategies, and temporal-aware modeling.
-
Lyra 2.0: Explorable Generative 3D Worlds
Lyra 2.0 produces persistent 3D-consistent video sequences for large explorable worlds by using per-frame geometry for information routing and self-augmented training to correct temporal drift.
-
A Semi-Automated Framework for 3D Reconstruction of Medieval Manuscript Miniatures
A pipeline using SAM segmentation and Hi3DGen mesh generation, evaluated on 69 medieval figures, produces usable 3D models for XR and tactile applications with Hi3DGen as the best starting point.
-
TripoSG: High-Fidelity 3D Shape Synthesis using Large-Scale Rectified Flow Models
TripoSG generates high-fidelity 3D meshes from input images via a large-scale rectified flow transformer and hybrid-trained 3D VAE on a custom 2-million-sample dataset, claiming state-of-the-art fidelity and generalization.
-
InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models
InstantMesh produces diverse, high-quality 3D meshes from single images in seconds by combining a multi-view diffusion model with a sparse-view large reconstruction model and optimizing directly on meshes.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
-
AmaraSpatial-10K: A Spatially and Semantically Aligned 3D Dataset for Spatial Computing and Embodied AI
AmaraSpatial-10K supplies 10K deployment-ready 3D assets with metric scaling and metadata, delivering 3.4x higher CLIP Recall@5 than Objaverse and 99.1% physics stability in Habitat-Sim.
-
UniMesh: Unifying 3D Mesh Understanding and Generation
UniMesh unifies 3D mesh generation and understanding in one model via a Mesh Head interface, Chain of Mesh iterative editing, and an Actor-Evaluator self-reflection loop.
-
FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation
FunCanon introduces functional object canonicalization with VLM affordances to create pose-aware action primitives for generalizable imitation learning in robotic manipulation.
- Stream3D: Sequential Multi-View 3D Generation via Evidential Memory
- OpenWorldLib: A Unified Codebase and Definition of Advanced World Models