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.
hub
Omniworld: A multi-domain and multi-modal dataset for 4d world modeling
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
fields
cs.CV 20representative citing papers
MemLearner introduces a learning-based adaptive context query method using query tokens in video world models to improve long-term scene consistency over rule-based retrieval.
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
M²-REPA decouples modality-specific features from diffusion intermediates and aligns them to complementary expert foundation models via a multi-modal alignment loss and modality-specific decoupling regularization for improved multimodal video generation.
PointDiT is a from-scratch pixel-space Diffusion Transformer for monocular 3D point map estimation that outperforms latent diffusion models in sharpness and ambiguous regions while using a simpler architecture.
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
MDA represents per-pixel depth as a mixture of distributions so that boundary pixels can align hypotheses with distinct surfaces instead of averaging into empty space.
Robust Dreamer uses Latent Gaussian Memory anchored to diffusion latents and Deviation Learning with a Dynamic Deviation Archive to reduce drift in long-horizon action-controlled image-to-video generation, reporting SOTA results on ScanNet, DL3DV, and OmniWorldGame.
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight benchmarks.
DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.
DexAC-WM improves FID, FVD, and PCK in high-DoF action-conditioned video prediction via structured action modeling and semantic grounding on EgoDex and EgoVerse.
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
citing papers explorer
-
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.
-
MemLearner: Learning to Query Context memory for Video World Models
MemLearner introduces a learning-based adaptive context query method using query tokens in video world models to improve long-term scene consistency over rule-based retrieval.
-
Geo-Align: Video Generation Alignment via Metric Geometry Reward
Geo-Align applies RL with a perceptual reward derived from 3D camera trajectory estimation to improve controllability and fidelity in video generation without paired training data.
-
Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models
M²-REPA decouples modality-specific features from diffusion intermediates and aligns them to complementary expert foundation models via a multi-modal alignment loss and modality-specific decoupling regularization for improved multimodal video generation.
-
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation
PointDiT is a from-scratch pixel-space Diffusion Transformer for monocular 3D point map estimation that outperforms latent diffusion models in sharpness and ambiguous regions while using a simpler architecture.
-
ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning
ICDepth adapts text-to-video diffusion transformers for video depth estimation via in-context conditioning, achieving SOTA results on benchmarks with 6-13x less training data than prior generative methods.
-
DisCo: World Models with Discrete Camera Motion Control
DisCo uses discrete action primitives for camera control in video world models to achieve more reliable action following than continuous trajectories.
-
Modeling Depth Ambiguity: A Mixture-Density Representation for Flying-Point-Free Depth Estimation
MDA represents per-pixel depth as a mixture of distributions so that boundary pixels can align hypotheses with distinct surfaces instead of averaging into empty space.
-
Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
Robust Dreamer uses Latent Gaussian Memory anchored to diffusion latents and Deviation Learning with a Dynamic Deviation Archive to reduce drift in long-horizon action-controlled image-to-video generation, reporting SOTA results on ScanNet, DL3DV, and OmniWorldGame.
-
Towards Consistent Video Geometry Estimation
One transformer, trained with random-sized temporal attention chunks, unifies offline, streaming, and long-video depth, normal, and point-map estimation and reports new best numbers on five public benchmarks.
-
Embody4D: A Generalist Data Engine for Embodied 4D World Modeling
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
-
Self-Improving 4D Perception via Self-Distillation
SelfEvo enables pretrained 4D perception models to self-improve on unlabeled videos via self-distillation, delivering up to 36.5% relative gains in video depth estimation and 20.1% in camera estimation across eight benchmarks.
-
Depth Anything 3: Recovering the Visual Space from Any Views
DA3 recovers consistent visual geometry from arbitrary views via a vanilla DINO transformer and depth-ray target, setting new SOTA on a visual geometry benchmark while outperforming DA2 on monocular depth.
-
Not All Actions Are Equal: Rethinking Conditioning for Dexterous World Model
DexAC-WM improves FID, FVD, and PCK in high-DoF action-conditioned video prediction via structured action modeling and semantic grounding on EgoDex and EgoVerse.
-
$R^3$: 3D Reconstruction via Relative Regression
R³ uses relative regression with confidence-weighted constraints from an MLP to support long-context offline and streaming 3D reconstruction without global coordinate assumptions.
-
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction
HorizonStream is a long-horizon Transformer that factorizes geometric evidence influence into channel-wise linear attention for long-range temporal propagation and local spatiotemporal attention for short-range matching, claiming stable generalization from 48-frame training to over 10,000-frame test
-
SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer
SANA-WM is a 2.6B-parameter efficient world model that synthesizes minute-scale 720p videos with 6-DoF camera control, trained on 213K public clips in 15 days on 64 H100s and runnable on single GPUs at 36x higher throughput than prior open baselines.
-
WildPose: A Unified Framework for Robust Pose Estimation in the Wild
WildPose unifies feedforward 3D features from MASt3R with differentiable bundle adjustment for robust monocular pose estimation across dynamic, static, and low-ego-motion scenes.
-
Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory
Matrix-Game 3.0 delivers 720p real-time video generation at 40 FPS with minute-scale memory consistency by combining residual self-correction training, camera-aware memory injection, and DMD-based autoregressive distillation on a 5B model.
- SCoPE: Sightline-Coordinate Positional Encoding for Video Diffusion Transformers