Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
hub
Texverse: A universe of 3d objects with high-resolution textures
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
fields
cs.CV 16representative citing papers
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.
HAT-4D presents an agentic VLM-plus-human-in-the-loop pipeline for monocular 4D multi-object interaction reconstruction and releases the MVOIK-4D benchmark.
NeuMatEx extracts spatially varying neural materials from multi-view images by using a learned LMRM prior for initialization followed by uncertainty-guided inverse path tracing optimization.
Helix4D generates high-quality dynamic 4D meshes from videos by extending Trellis2 with sliding-window cross-frame attention anchored on the first frame and a repurposed 4D temporal encoding.
H-OmniStereo trains a stereo matcher on 2.8 million synthetic equirectangular pairs and adds a heading-aligned normal prior to improve zero-shot accuracy and generalization on out-of-domain and real omnidirectional data.
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
LingBot-Map is a streaming 3D reconstruction model built on a geometric context transformer that combines anchor context, pose-reference window, and trajectory memory to deliver accurate, drift-resistant results at 20 FPS over sequences longer than 10,000 frames.
Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials than prior methods.
Sat2City v2 adapts a pretrained native 3D latent model to generate controllable textured 3D city assets from satellite images via geometry flow fine-tuning and anchored texturing on a collected real dataset.
A multi-view feed-forward transformer provides initial poses and geometry from calibrated videos, followed by physics-aware Gaussian optimization with tetrahedral and collision constraints to produce robust 4D hand-object reconstructions.
Artiverse is a new dataset of 5.4K human-authored articulated 3D objects with detailed annotations for parts, multi-DoF joints, interior structures, and physical attributes to enable functional modeling and physics-based interaction.
EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.
A literature survey that organizes neural 3D mesh texturing methods into a taxonomy spanning early GAN-based approaches to modern diffusion pipelines, while reviewing architectures, datasets, evaluation, and open challenges.
citing papers explorer
-
Every9D-21M: Large-Scale Real-World 9D Canonicalization of Everyday Objects
Every9D-21M supplies 21.8M real-world 9D pose annotations for 700 everyday categories by propagating manual canonical poses through cross-instance alignment in object-centric videos and verifying them multiview.
-
SpatialBench: Is Your Spatial Foundation Model an All-Round Player?
SpatialBench evaluates 41 spatial foundation models across 6 paradigms and 5 task suites, finds they are not all-round players, and introduces the DA-Next-5M dataset plus DA-Next baseline model.
-
Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models
Ink3D decouples geometry from texture by generating dense orbit videos with a conditional video model and baking them via a neural optimizer to produce complex 3D textures.
-
Mesh BDF: Barycentric Dominance Field for 3D Native Mesh Generation
Barycentric Dominance Field converts discrete mesh connectivity into a continuous surface signal that diffusion models can use directly for higher-quality native 3D mesh generation.
-
HAT-4D: Lifting Monocular Video for 4D Multi-Object Interactions via Human-Agent Collaboration
HAT-4D presents an agentic VLM-plus-human-in-the-loop pipeline for monocular 4D multi-object interaction reconstruction and releases the MVOIK-4D benchmark.
-
Extracting Neural Materials from Multi-view Images
NeuMatEx extracts spatially varying neural materials from multi-view images by using a learned LMRM prior for initialization followed by uncertainty-guided inverse path tracing optimization.
-
Helix4D: Complex 4D Mesh Generation
Helix4D generates high-quality dynamic 4D meshes from videos by extending Trellis2 with sliding-window cross-frame attention anchored on the first frame and a repurposed 4D temporal encoding.
-
H-OmniStereo: Zero-Shot Omnidirectional Stereo Matching with Heading-Aligned Normal Priors
H-OmniStereo trains a stereo matcher on 2.8 million synthetic equirectangular pairs and adds a heading-aligned normal prior to improve zero-shot accuracy and generalization on out-of-domain and real omnidirectional data.
-
Camera Control for Text-to-Image Generation via Learning Viewpoint Tokens
Viewpoint tokens learned on a mixed 3D-rendered and photorealistic dataset enable precise camera control in text-to-image generation while factorizing geometry from appearance and transferring to unseen object categories.
-
Geometric Context Transformer for Streaming 3D Reconstruction
LingBot-Map is a streaming 3D reconstruction model built on a geometric context transformer that combines anchor context, pose-reference window, and trajectory memory to deliver accurate, drift-resistant results at 20 FPS over sequences longer than 10,000 frames.
-
Native and Compact Structured Latents for 3D Generation
Introduces O-Voxel omni-voxel representation and Sparse Compression VAE for structured native 3D latents, enabling efficient training of large flow-matching models that produce higher-quality geometry and materials than prior methods.
-
Sat2City v2: Native 3D City Asset Generation from a Single Satellite Image
Sat2City v2 adapts a pretrained native 3D latent model to generate controllable textured 3D city assets from satellite images via geometry flow fine-tuning and anchored texturing on a collected real dataset.
-
High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians
A multi-view feed-forward transformer provides initial poses and geometry from calibrated videos, followed by physics-aware Gaussian optimization with tetrahedral and collision constraints to produce robust 4D hand-object reconstructions.
-
Artiverse: A Diverse and Physically Grounded Dataset for Articulated Objects
Artiverse is a new dataset of 5.4K human-authored articulated 3D objects with detailed annotations for parts, multi-DoF joints, interior structures, and physical attributes to enable functional modeling and physics-based interaction.
-
EVA01: Unified Native 3D Understanding and Generation via Mixture-of-Transformers
EVA01 introduces a Mixture-of-Transformers model that natively adds 3D mesh understanding, generation, and multi-turn editing to MLLMs by decoupling understanding and generation experts with shared global self-attention.
-
Advances in Neural 3D Mesh Texturing: A Survey
A literature survey that organizes neural 3D mesh texturing methods into a taxonomy spanning early GAN-based approaches to modern diffusion pipelines, while reviewing architectures, datasets, evaluation, and open challenges.