NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
144 results for “keyword:"3d reconstruction"” in ICLR 2027. 62 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]KB-Splatting: Differentiable Kaiser-Bessel Splatting for Real X-ray Projection-Enabled CT Reconstruction▲3.0k2.33
[PDF]One Framework, Diverse Information Deficiencies: Towards Unified 3D Gaussian Reconstruction under Imperfect Observations▼4.3k2.00
[PDF]LaRI3R: Bidirectional Ray Intersections for Occluded 3D Scene Reconstruction from Two Views▲3952.67
[PDF]Extending 3D Foundation Models from to Any Central Camera with Distortion Awareness Token▼1.2k3.00
[PDF]CoSplat: Complementary Surface Geometry Learning for Generalizable Surface Reconstruction▼2443.33
[PDF]QuadVGGT: Quotient Attention for Accelerating Dense-Token Inference in Visual Geometry Grounded Transformers▲5103.00
[PDF]ZoomSplat: Rethinking Multi-view Frequency Bounds for Anti-aliased Feed-forward 3D Gaussian Splatting▲3952.67
[PDF]UniGS-SLAM: Monocular Gaussian SLAM with Enhanced Geometry and Open-Vocabulary Semantics▲5.4k3.00
[PDF]Rotation Is Token-Blind: A Structural Criterion for Post-Training Quantization of Feed-Forward Geometry Transformers▲5.4k3.00
[PDF]ArtModeling: An Instance-Matched Dataset and Benchmark for Articulated-Object Perception and Dynamics▲5103.00
[PDF]ObjAligner: Feed-Forward Object Pose Estimation and Reconstruction via Shared Geometry▼5.8k2.33
[PDF]4DHOISolver: Efficient and Accurate Human–Object Motion Reconstruction from Monocular Videos▼4.3k2.00
[PDF]LucidLyra: Feed-Forward Generative 3D Scene Reconstruction and Joint Understanding via Multi-Task Distillation▲5103.00
[PDF]T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images▲1.7k3.33
[PDF]RemixGS: Scalable Feed-Forward Gaussian Splatting with View-Register Mixing and Interleaved Gaussian Queries▼4.3k2.00
[PDF]IMSCENE: AN AGENTIC FRAMEWORK FOR RECONSTRUCTING SIMULATION-READY 3D SCENES FROM A SINGLE IMAGE▲3952.67
[PDF]Geometry at the Last Mile: Beyond Local Appearance-Only Correspondence Search in Feature Matching▲5.4k3.00
[PDF]Reason the Scene, Reconstruct the Space, Render the Unseen: TinkerCube for Spatial Intelligence▼5.8k2.33
Withdrawn or desk rejected (62)
[PDF]What a 3D Reconstruction Benchmark Can and Cannot Tell About Geometric Foundation ModelsWithdrawn2.00
[PDF]OpenU3R: Towards Zero-Shot Generalizable Feed-Forward Open-Vocabulary Understanding and 3D ReconstructionWithdrawn2.00
[PDF]ReasonFit: Coupling VLM Structural Reasoning with Differentiable Multi-view Fitting for Primitive-Based ReconstructionWithdrawn1.67
[PDF]Same Geometry, Different Scores: Auditing Coordinate and Scale Dependence in Geometric Video EvaluationWithdrawn1.67