mlsanityData to 14 Oct 2026

SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering

arXiv 2503.12024 ↗First posted 15 Mar 2025cs.CVcited by 15

Not on the map. Why?

Abstract (arXiv)

Recent progress in 3D/4D scene generation emphasizes the importance of physical alignment throughout video generation and scene reconstruction. However, existing methods improve the alignment separately at each stage, making it difficult to manage subtle misalignments arising from another stage. Here, we present SteerX, a zero-shot inference-time steering method that unifies scene reconstruction into the generation process, tilting data distributions toward better geometric alignment. To this end, we introduce two geometric reward functions for 3D/4D scene generation by using pose-free feed-forward scene reconstruction models. Through extensive experiments, we demonstrate the effectiveness of SteerX in improving 3D/4D scene generation.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 78 of its 90 references that are in the map. First posted on arXiv 15 Mar 2025.

Builds on

78 of 90 references.

References · 78

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  4. 2023Segment Anythingcited by 8,234
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,226
  7. 2022Scalable Diffusion Models with Transformerscited by 6,054
  8. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,117
  9. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,025
  10. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,581
  11. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  12. 2022Video Diffusion Modelscited by 2,305
38 more
  1. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
  2. 2021Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fieldscited by 1,964
  3. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
  4. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,660
  5. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  6. 2022Diffusion Posterior Sampling for General Noisy Inverse Problemscited by 1,416
  7. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  8. 2022Magic3D: High-Resolution Text-to-3D Content Creationcited by 1,290
  9. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,219
  10. 2020Nerfies: Deformable Neural Radiance Fieldscited by 1,198
  11. 20234D Gaussian Splatting for Real-Time Dynamic Scene Renderingcited by 1,157
  12. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
  13. 2023Training Diffusion Models with Reinforcement Learningcited by 982
  14. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  15. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  16. 2020Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenescited by 751
  17. 2023Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creationcited by 687
  18. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  19. 2023Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fieldscited by 671
  20. 2023Mip-Splatting: Alias-free 3D Gaussian Splattingcited by 667
  21. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  22. 2023SyncDreamer: Generating Multiview-consistent Images from a Single-view Imagecited by 645
  23. 2022Score Jacobian Chaining: Lifting Pretrained 2D Diffusion Models for 3D Generationcited by 597
  24. 2024LTX-Video: Realtime Video Latent Diffusioncited by 581
  25. 2023MotionCtrl: A Unified and Flexible Motion Controller for Video Generationcited by 580
  26. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  27. 2022Latent-NeRF for Shape-Guided Generation of 3D Shapes and Texturescited by 506
  28. 2024CameraCtrl: Enabling Camera Control for Text-to-Video Generationcited by 460
  29. 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
  30. 2024CAT3D: Create Anything in 3D with Multi-View Diffusion Modelscited by 432
  31. 2024ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesiscited by 403
  32. 2021Advances in Neural Renderingcited by 365
  33. 2023Splatter Image: Ultra-Fast Single-View 3D Reconstructioncited by 364
  34. 2022Flexible Diffusion Modeling of Long Videoscited by 294
  35. 2024Shape of Motion: 4D Reconstruction from a Single Videocited by 250
  36. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  37. 2020Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Imagecited by 243
  38. 2023Practical and Asymptotically Exact Conditional Sampling in Diffusion Modelscited by 232

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 4; 2026: 11.

15 papers.

Sort:

By area:

  1. 2026Inference-time Physics Alignment of Video Generative Models with Latent World Modelscited by 37
  2. 2026VGGRPO: Towards World-Consistent Video Generation with 4D Latent Rewardcited by 24
  3. 2025Diffusion models for inverse problemscited by 16
  4. 2025See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpaintingcited by 12
  5. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  6. 2025ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encodingcited by 11
  7. 2026World-R1: Reinforcing 3D Constraints for Text-to-Video Generationcited by 11
  8. 2026VideoWeave: Unlocking Geometric Consistency in Video Generation via Joint Geometry-Video Modelingcited by 7
  9. 2026Feed-Forward 3D Scene Modeling: A Problem-Driven Perspectivecited by 6
  10. 2026Geo-Align: Video Generation Alignment via Metric Geometry Rewardcited by 3
  11. 2026Stitched Value Model for Diffusion Alignmentcited by 2
  12. 2026SierpinskiCam: Camera-Controlled Video Retaking with Sierpinski Triangle Pattern Cuescited by 2
3 more
  1. 2026PE-Field 4D: Video Generation Models as Canvascited by 0
  2. 2026FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlowcited by 0
  3. 2026GeoFix: Geometry Fixing for 4D Consistent Generationcited by 0