GLADOS reconstructs 3D geometry from disjoint views by generating intermediate perspectives, performing robust coarse alignment that tolerates generative inconsistencies, and iteratively expanding context for consistency.
hub Canonical reference
MVDream: Multi-view Diffusion for 3D Generation
Canonical reference. 100% of citing Pith papers cite this work as background.
44
Pith papers citing it
Background
100% of classified citations
abstract
We introduce MVDream, a diffusion model that is able to generate consistent multi-view images from a given text prompt. Learning from both 2D and 3D data, a multi-view diffusion model can achieve the generalizability of 2D diffusion models and the consistency of 3D renderings. We demonstrate that such a multi-view diffusion model is implicitly a generalizable 3D prior agnostic to 3D representations. It can be applied to 3D generation via Score Distillation Sampling, significantly enhancing the consistency and stability of existing 2D-lifting methods. It can also learn new concepts from a few 2D examples, akin to DreamBooth, but for 3D generation.
hub tools
citation-role summary
background 9
citation-polarity summary
roles
background 9polarities
background 9representative citing papers
Introduces the first passive source attribution benchmark for 22 generative 3D models and a Transformer achieving 97.22% accuracy under full supervision and 77.17% with 1% training data.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
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.
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in realism and consistency.
SparseCam4D achieves spatio-temporally consistent high-fidelity 4D reconstruction from sparse cameras via a Spatio-Temporal Distortion Field that corrects inconsistencies in generative observations.
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
ATATA enables fast joint inference of structurally aligned pairs using Rectified Flow models via segment transport, improving state-of-the-art for image and video generation while matching 3D quality at much higher speed.
Affostruction reconstructs full 3D object geometry from partial RGBD views and grounds text-based affordances on both visible and unobserved surfaces, reporting large gains over prior methods.
SV-GS estimates a time-dependent skeleton pose plus fine deformations to enable 4D Gaussian splatting from sparse views, outperforming prior sparse methods by up to 34% PSNR on synthetic data and matching dense monocular baselines on real data with far fewer frames.
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
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.
HAD uses multi-view reasoning from a pre-trained feedforward NVS network to estimate and mask hallucination scores in diffusion priors, reducing artifacts and achieving SOTA novel view synthesis in sparse-view 3D reconstruction.
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.
Imagining in 360° decouples visual search into a single-step probabilistic semantic layout predictor and an actor, removing the need for multi-turn CoT reasoning and trajectory annotations while improving efficiency in 360° environments.
Velox compresses dynamic point clouds into latent tokens that support geometry via 4D surface modeling and appearance via 3D Gaussians, showing strong results on video-to-4D generation, tracking, and image-to-4D cloth simulation.
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
REVIVE 3D generates voluminous 3D assets from flat 2D images via an inflated prior construction followed by latent-space refinement, plus new metrics for volume and flatness validated by user study.
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.
A two-stage method synthesizes multi-view 2D motion data from internet video keypoints and trains a camera-conditioned diffusion model to recover globally consistent 3D human motion and HOI in world space.
HandDreamer is the first zero-shot text-to-3D method for hands that uses MANO initialization, skeleton-guided diffusion, and corrective shape guidance to produce view-consistent models.
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
citing papers explorer
-
Mind the Gap: Geometrically Accurate Generative Reconstruction from Disjoint Views
GLADOS reconstructs 3D geometry from disjoint views by generating intermediate perspectives, performing robust coarse alignment that tolerates generative inconsistencies, and iteratively expanding context for consistency.
-
Who Generated This 3D Asset? Learning Source Attribution for Generative 3D Models
Introduces the first passive source attribution benchmark for 22 generative 3D models and a Transformer achieving 97.22% accuracy under full supervision and 77.17% with 1% training data.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
DEVIS-GRPO: Unleashing GRPO on Dynamic Extreme View Synthesis
DEVIS-GRPO applies online policy gradients with an accumulative small-to-large view sampling strategy and multi-level rewards to improve trajectory-controlled extreme view video generation, reporting gains on Kubric-4D, iPhone, and DL3DV datasets.
-
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.
-
Geometrically Consistent Multi-View Scene Generation from Freehand Sketches
A framework generates consistent multi-view scenes from one freehand sketch via a ~9k-sample dataset, Parallel Camera-Aware Attention Adapters, and Sparse Correspondence Supervision Loss, outperforming baselines in realism and consistency.
-
SparseCam4D: Spatio-Temporally Consistent 4D Reconstruction from Sparse Cameras
SparseCam4D achieves spatio-temporally consistent high-fidelity 4D reconstruction from sparse cameras via a Spatio-Temporal Distortion Field that corrects inconsistencies in generative observations.
-
Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards
SOLACE improves text-to-image generation by using intrinsic self-confidence rewards from noise reconstruction accuracy during reinforcement learning post-training without external supervision.
-
ATATA: One Algorithm to Align Them All
ATATA enables fast joint inference of structurally aligned pairs using Rectified Flow models via segment transport, improving state-of-the-art for image and video generation while matching 3D quality at much higher speed.
-
Affostruction: 3D Affordance Grounding with Generative Reconstruction
Affostruction reconstructs full 3D object geometry from partial RGBD views and grounds text-based affordances on both visible and unobserved surfaces, reporting large gains over prior methods.
-
SV-GS: Sparse View 4D Reconstruction with Skeleton-Driven Gaussian Splatting
SV-GS estimates a time-dependent skeleton pose plus fine deformations to enable 4D Gaussian splatting from sparse views, outperforming prior sparse methods by up to 34% PSNR on synthetic data and matching dense monocular baselines on real data with far fewer frames.
-
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
-
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.
-
HAD: Hallucination-Aware Diffusion Priors for 3D Reconstruction
HAD uses multi-view reasoning from a pre-trained feedforward NVS network to estimate and mask hallucination scores in diffusion priors, reducing artifacts and achieving SOTA novel view synthesis in sparse-view 3D reconstruction.
-
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction
GeoQuery replaces corrupted rendering features with geometry-aligned proxy queries and restricts cross-view attention to local windows, enabling robust diffusion-based refinement under extreme view sparsity.
-
Beyond Thinking: Imagining in 360$^\circ$ for Humanoid Visual Search
Imagining in 360° decouples visual search into a single-step probabilistic semantic layout predictor and an actor, removing the need for multi-turn CoT reasoning and trajectory annotations while improving efficiency in 360° environments.
-
Velox: Learning Representations of 4D Geometry and Appearance
Velox compresses dynamic point clouds into latent tokens that support geometry via 4D surface modeling and appearance via 3D Gaussians, showing strong results on video-to-4D generation, tracking, and image-to-4D cloth simulation.
-
Structured 3D Latents Are Surprisingly Powerful: Unleashing Generalizable Style with 2D Diffusion
DiLAST optimizes 3D latents via guidance from a 2D diffusion model to enable generalizable style transfer for OOD styles in 3D asset generation.
-
REVIVE 3D: Refinement via Encoded Voluminous Inflated prior for Volume Enhancement
REVIVE 3D generates voluminous 3D assets from flat 2D images via an inflated prior construction followed by latent-space refinement, plus new metrics for volume and flatness validated by user study.
-
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.
-
AnyLift: Scaling Motion Reconstruction from Internet Videos via 2D Diffusion
A two-stage method synthesizes multi-view 2D motion data from internet video keypoints and trains a camera-conditioned diffusion model to recover globally consistent 3D human motion and HOI in world space.
-
HandDreamer: Zero-Shot Text to 3D Hand Model Generation using Corrective Hand Shape Guidance
HandDreamer is the first zero-shot text-to-3D method for hands that uses MANO initialization, skeleton-guided diffusion, and corrective shape guidance to produce view-consistent models.
-
Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas
Stepper uses stepwise panoramic expansion with a multi-view 360-degree diffusion model and geometry reconstruction to produce high-fidelity, structurally consistent immersive 3D scenes from text.
-
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.
-
Motion-2-To-3: Leveraging 2D Motion Data for 3D Motion Generations
A framework disentangles local joint motion from global movement, trains a 2D local generator on text-2D pairs, then fine-tunes on 3D data to output view-consistent 3D motions.
-
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.
-
BoostDream: Efficient Refining for High-Quality Text-to-3D Generation from Multi-View Diffusion
BoostDream refines coarse feed-forward text-to-3D assets via 3D distillation, multi-view SDS loss from a 2D diffusion model, and prompt-consistent normal maps to produce higher-quality results more efficiently than standard SDS.
-
Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets
Stable Video Diffusion scales latent video diffusion models via text-to-image pretraining, video pretraining on curated data, and high-quality finetuning to produce competitive text-to-video and image-to-video results while enabling motion LoRA and multi-view 3D applications.
-
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
SyncDreamer produces multiview-consistent images from a single input image by jointly modeling their distribution and synchronizing intermediate diffusion states via 3D-aware attention.
-
VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow Matching
VolFill uses a hybrid 3D VAE to compress sparse truncated unsigned distance function grids into latent space and a latent Diffusion Transformer to denoise complete scenes, conditioned on geometry foundation models, outperforming baselines on SCRREAM and NRGB-D datasets.
-
Efficient 3D Content Reconstruction and Generation
Presents Instant3D for rapid text/image-to-3D generation via multi-view diffusion plus feed-forward reconstruction, and FastMap for 10x faster structure-from-motion with comparable accuracy.
-
DreamEdit3D: Personalization of Multi-View Diffusion Models for 3D Editing
DreamEdit3D learns separate token embeddings for segmented object components via two-phase multi-view optimization to enable text-guided 3D editing with consistent image generation and mesh reconstruction.
-
DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion
DecoRec decomposes single-view 3D scene reconstruction into per-object diffusion reconstructions followed by a differentiable rendering and diffusion-guided merging pipeline.
-
Pose-Aware Diffusion for 3D Generation
PAD synthesizes 3D geometry in observation space via depth unprojection as anchor to eliminate pose ambiguity in image-to-3D generation.
-
Asset Harvester: Extracting 3D Assets from Autonomous Driving Logs for Simulation
Asset Harvester converts sparse in-the-wild object observations from AV driving logs into complete simulation-ready 3D assets via data curation, geometry-aware preprocessing, and a SparseViewDiT model that couples sparse-view multiview generation with 3D Gaussian lifting.
-
DreamLifting: A Plug-in Module Lifting MV Diffusion Models for 3D Asset Generation
LGAA is a modular adapter framework that lifts multi-view diffusion models to produce 2D Gaussian Splats with PBR channels for high-quality relightable 3D mesh extraction using data-efficient finetuning on 69k instances.
-
ConsDreamer: Advancing Multi-View Consistency for Zero-Shot Text-to-3D Generation
ConsDreamer refines conditional and unconditional terms in score distillation via view disentanglement and geometric consistency loss to reduce the Janus problem in zero-shot text-to-3D.
-
TripoSR: Fast 3D Object Reconstruction from a Single Image
TripoSR generates 3D meshes from single images in under 0.5 seconds using an improved transformer architecture over LRM.
-
Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model
Zero123++ produces high-quality 3D-consistent multi-view images from a single input by fine-tuning Stable Diffusion with targeted conditioning and training methods.
-
Dual-Stream EEG Decoding for 3D Visual Perception
Dual-stream EEG decoder separates identity and orientation to support 3D reconstruction from neural signals via circular regression and conditioned diffusion.
-
AnimateAnyMesh++: A Flexible 4D Foundation Model for High-Fidelity Text-Driven Mesh Animation
AnimateAnyMesh++ animates arbitrary 3D meshes from text using an expanded 300K-identity DyMesh-XL dataset, a power-law topology-aware DyMeshVAE-Flex, and a variable-length rectified-flow generator to produce semantically accurate, temporally coherent animations in seconds.
-
Cosmos World Foundation Model Platform for Physical AI
The Cosmos platform supplies open-source pre-trained world models and supporting tools for building fine-tunable digital world simulations to train Physical AI.
- Stream3D: Sequential Multi-View 3D Generation via Evidential Memory