mlsanityData to 14 Oct 2026

FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views

arXiv 2502.12138 ↗First posted 17 Feb 2025cs.CVcited by 180

Not on the map. Why?

Abstract (arXiv)

We present FLARE, a feed-forward model designed to infer high-quality camera poses and 3D geometry from uncalibrated sparse-view images (i.e., as few as 2-8 inputs), which is a challenging yet practical setting in real-world applications. Our solution features a cascaded learning paradigm with camera pose serving as the critical bridge, recognizing its essential role in mapping 3D structures onto 2D image planes. Concretely, FLARE starts with camera pose estimation, whose results condition the subsequent learning of geometric structure and appearance, optimized through the objectives of geometry reconstruction and novel-view synthesis. Utilizing large-scale public datasets for training, our method delivers state-of-the-art performance in the tasks of pose estimation, geometry reconstruction, and novel view synthesis, while maintaining the inference efficiency (i.e., less than 0.5 seconds). The project page and code can be found at: https://zhanghe3z.github.io/FLARE/

Key facts. Cited by 180 papers in the map (data through 14 Oct 2026). Builds on 75 of its 99 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

75 of 99 references.

References · 75

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2019DeepSDF: Learning Continuous Signed Distance Functions for Shape Representationcited by 2,689
  3. 2019Scalability in Perception for Autonomous Driving: Waymo Open Datasetcited by 2,451
  4. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  5. 2021Vision Transformers for Dense Predictioncited by 1,803
  6. 2020pixelNeRF: Neural Radiance Fields from One or Few Imagescited by 1,584
  7. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,567
  8. 2019SuperGlue: Learning Feature Matching with Graph Neural Networkscited by 1,443
  9. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  10. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,320
  11. 2021Efficient Geometry-aware 3D Generative Adversarial Networkscited by 1,205
  12. 2021LoFTR: Detector-Free Local Feature Matching with Transformerscited by 984
38 more
  1. 2024Grounding Image Matching in 3D with MASt3Rcited by 983
  2. 2019Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representationscited by 864
  3. 2023LRM: Large Reconstruction Model for Single Image to 3Dcited by 849
  4. 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 788
  5. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 764
  6. 2021MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereocited by 740
  7. 2018MegaDepth: Learning Single-View Depth Prediction from Internet Photoscited by 737
  8. 2021IBRNet: Learning Multi-View Image-Based Renderingcited by 703
  9. 2023pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstructioncited by 684
  10. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 652
  11. 2021BARF: Bundle-Adjusting Neural Radiance Fieldscited by 642
  12. 2024MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Imagescited by 566
  13. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
  14. 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 490
  15. 2021Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesiscited by 464
  16. 2021ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Datacited by 454
  17. 2023SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAMcited by 388
  18. 2023Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Modelcited by 378
  19. 2021Advances in Neural Renderingcited by 365
  20. 2019D2-Net: A Trainable CNN for Joint Detection and Description of Local Featurescited by 326
  21. 2016LIFT: Learned Invariant Feature Transformcited by 306
  22. 2024GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generationcited by 301
  23. 2024gsplat: An Open-Source Library for Gaussian Splattingcited by 285
  24. 20243D Reconstruction with Spatial Memorycited by 277
  25. 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 254
  26. 2024No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Imagescited by 248
  27. 2022NoPe-NeRF: Optimising Neural Radiance Field with No Pose Priorcited by 235
  28. 2021Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representationscited by 227
  29. 2023Visual Geometry Grounded Deep Structure From Motioncited by 227
  30. 2020Image Matching across Wide Baselines: From Paper to Practicecited by 225
  31. 2018Stereo Magnification: Learning View Synthesis using Multiplane Imagescited by 211
  32. 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 207
  33. 2021Self-Calibrating Neural Radiance Fieldscited by 204
  34. 2021Pixel-Perfect Structure-from-Motion with Featuremetric Refinementcited by 200
  35. 2022SPARF: Neural Radiance Fields from Sparse and Noisy Posescited by 195
  36. 2023COLMAP-Free 3D Gaussian Splattingcited by 193
  37. 2024Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairscited by 178
  38. 2022SparseNeuS: Fast Generalizable Neural Surface Reconstruction from Sparse Viewscited by 177

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 81; 2026: 99.

180 papers.

Sort:

By area:

  1. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  2. 2025Depth Anything 3: Recovering the Visual Space from Any Viewscited by 692
  3. 2025π3: Permutation-Equivariant Visual Geometry Learningcited by 319
  4. 2025AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Viewscited by 243
  5. 2025Streaming 4D Visual Geometry Transformercited by 161
  6. 2025Video World Models with Long-term Spatial Memorycited by 136
  7. 2025CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Modelscited by 98
  8. 2025FastVGGT: Training-Free Acceleration of Visual Geometry Transformercited by 98
  9. 2025Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modelingcited by 96
  10. 2025RayZer: A Self-supervised Large View Synthesis Modelcited by 77
  11. 20253DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understandingcited by 70
  12. 2025WorldMirror: Universal 3D World Reconstruction with Any-Prior Promptingcited by 67
38 more
  1. 2025OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modelingcited by 62
  2. 2025Bolt3D: Generating 3D Scenes in Secondscited by 59
  3. 2025SceneGen: Single-Image 3D Scene Generation in One Feedforward Passcited by 54
  4. 2026NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videoscited by 46
  5. 2025LONG3R: Long Sequence Streaming 3D Reconstructioncited by 45
  6. 2025G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoningcited by 44
  7. 2026HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worldscited by 44
  8. 2025FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Predictioncited by 38
  9. 2025YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splattingcited by 37
  10. 2026LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstructioncited by 37
  11. 2025MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Secondcited by 35
  12. 2025WinT3R: Window-Based Streaming Reconstruction with Camera Token Poolcited by 35
  13. 2026V-DPM: 4D Video Reconstruction with Dynamic Point Mapscited by 34
  14. 2026Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstructioncited by 31
  15. 2025VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstructioncited by 28
  16. 2025Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Surveycited by 27
  17. 2026ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Trainingcited by 26
  18. 2026VGGT-Omegacited by 26
  19. 2025Block-Sparse Global Attention for Efficient Multi-View Geometry Transformerscited by 23
  20. 2025MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Expertscited by 21
  21. 2025SAIL-Recon: Large SfM by Augmenting Scene Regression with Localizationcited by 20
  22. 2025AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backendcited by 20
  23. 2025iLRM: An Iterative Large 3D Reconstruction Modelcited by 19
  24. 2025A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generationcited by 19
  25. 2026VGG-T3: Offline Feed-Forward 3D Reconstruction at Scalecited by 18
  26. 2025FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attentioncited by 17
  27. 2025SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observationscited by 16
  28. 2025VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Framescited by 15
  29. 20254Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generationcited by 14
  30. 2025Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splattingcited by 14
  31. 2025Revisiting Depth Representations for Feed-Forward 3D Gaussian Splattingcited by 12
  32. 2025Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generatorcited by 11
  33. 2025Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splattingcited by 11
  34. 2025Can Video Diffusion Model Reconstruct 4D Geometry?cited by 10
  35. 20254D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimationcited by 10
  36. 2025Taming Camera-Controlled Video Generation with Verifiable Geometry Rewardcited by 10
  37. 2025ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representationcited by 9
  38. 2026UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Passcited by 9

50 most cited of 180 All 180 (JSON)