Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images

• URL: http://arxiv.org/abs/2604.10573v1
• Date: Sun, 12 Apr 2026 10:36:18 GMT
• Title: Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images
• Abstract summary: UniSplat is a feed-forward framework for learning 3D representations from unposed multi-view images.<n>We introduce a dual-masking strategy that strengthens geometry induction in the encoder.<n>Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies.<n>Third, we introduce a pose-conditioned recalibration mechanism that interrelates predicted 3D point and semantic maps into the image plane.
• Score: 81.94999489820974
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Robust 3D representation learning forms the perceptual foundation of spatial intelligence, enabling downstream tasks in scene understanding and embodied AI. However, learning such representations directly from unposed multi-view images remains challenging. Recent self-supervised methods attempt to unify geometry, appearance, and semantics in a feed-forward manner, but they often suffer from weak geometry induction, limited appearance detail, and inconsistencies between geometry and semantics. We introduce UniSplat, a feed-forward framework designed to address these limitations through three complementary components. First, we propose a dual-masking strategy that strengthens geometry induction in the encoder. By masking both encoder and decoder tokens, and targeting decoder masks toward geometry-rich regions, the model is forced to infer structural information from incomplete visual cues, yielding geometry-aware representations even under unposed inputs. Second, we develop a coarse-to-fine Gaussian splatting strategy that reduces appearance-semantics inconsistencies by progressively refining the radiance field. Finally, to enforce geometric-semantic consistency, we introduce a pose-conditioned recalibration mechanism that interrelates the outputs of multiple heads by re-projecting predicted 3D point and semantic maps into the image plane using estimated camera parameters, and aligning them with corresponding RGB and semantic predictions to ensure cross-task consistency, thereby resolving geometry-semantic mismatches. Together, these components yield unified 3D representations that are robust to unposed, sparse-view inputs and generalize across diverse tasks, laying a perceptual foundation for spatial intelligence.

Related papers

• FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views [34.14517479047999]
  This paper introduces FF3R, a fully annotation-free feed-forward framework that unifies geometric and semantic reasoning from unconstrained multi-view image sequences.<n>Unlike previous methods, FF3R does not require camera poses, depth maps, or semantic labels, relying solely on rendering supervision for RGB and feature maps.<n>Two key innovations: (i) a Token-wise Fusion Module that enriches geometry tokens with semantic context via cross-attention, and (ii) a Semantic-Geometry Mutual Boosting mechanism combining geometry-guided feature warping for global consistency with semantic-aware voxelization for local coherence.
  arXiv  Detail & Related papers  (2026-04-10T19:45:24Z)
• Learning Human Visual Attention on 3D Surfaces through Geometry-Queried Semantic Priors [0.0]
  We introduce SemGeo-AttentionNet, a dual-stream architecture that formalizes the interplay between geometric processing and semantic recognition.<n>We extend our framework to temporal scanpath generation through reinforcement learning.<n> Evaluation on SAL3D, NUS3D and 3DVA datasets demonstrates substantial improvements.
  arXiv  Detail & Related papers  (2026-02-06T06:15:38Z)
• IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction [82.53307702809606]
  Humans naturally perceive the geometric structure and semantic content of a 3D world as intertwined dimensions.<n>We propose InstanceGrounded Geometry Transformer (IGGT) to unify the knowledge for both spatial reconstruction and instance-level contextual understanding.
  arXiv  Detail & Related papers  (2025-10-26T14:57:44Z)
• Seeing 3D Through 2D Lenses: 3D Few-Shot Class-Incremental Learning via Cross-Modal Geometric Rectification [59.17489431187807]
  We propose a framework that enhances 3D geometric fidelity by leveraging CLIP's hierarchical spatial semantics.<n>Our method significantly improves 3D few-shot class-incremental learning, achieving superior geometric coherence and robustness to texture bias.
  arXiv  Detail & Related papers  (2025-09-18T13:45:08Z)
• Reg3D: Reconstructive Geometry Instruction Tuning for 3D Scene Understanding [6.7958985137291235]
  Reg3D is a novel Reconstructive Geometry Instruction Tuning framework that incorporates geometry-aware supervision directly into the training process.<n>Our key insight is that effective 3D understanding requires reconstructing underlying geometric structures rather than merely describing them.<n>Experiments on ScanQA, Scan2Cap, ScanRefer, and SQA3D demonstrate that Reg3D delivers substantial performance improvements.
  arXiv  Detail & Related papers  (2025-09-03T18:36:44Z)
• SeqAffordSplat: Scene-level Sequential Affordance Reasoning on 3D Gaussian Splatting [85.87902260102652]
  We introduce the novel task of Sequential 3D Gaussian Affordance Reasoning.<n>We then propose SeqSplatNet, an end-to-end framework that directly maps an instruction to a sequence of 3D affordance masks.<n>Our method sets a new state-of-the-art on our challenging benchmark, effectively advancing affordance reasoning from single-step interactions to complex, sequential tasks at the scene level.
  arXiv  Detail & Related papers  (2025-07-31T17:56:55Z)
• Large Spatial Model: End-to-end Unposed Images to Semantic 3D [79.94479633598102]
  Large Spatial Model (LSM) processes unposed RGB images directly into semantic radiance fields. LSM simultaneously estimates geometry, appearance, and semantics in a single feed-forward operation. It can generate versatile label maps by interacting with language at novel viewpoints.
  arXiv  Detail & Related papers  (2024-10-24T17:54:42Z)
• Self-Supervised Image Representation Learning with Geometric Set Consistency [50.12720780102395]
  We propose a method for self-supervised image representation learning under the guidance of 3D geometric consistency. Specifically, we introduce 3D geometric consistency into a contrastive learning framework to enforce the feature consistency within image views.
  arXiv  Detail & Related papers  (2022-03-29T08:57:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.