arXiv:2604.19609v2 Announce Type: replace Abstract: Transformers have become a common foundation across deep learning, yet 3D scene understanding still relies on specialized backbones with strong dom...
arXiv:2608.23850v1 Announce Type: new Abstract: Foundational visual features such as DINO have played a critical role across modern computer vision, and have recently become key components in multi-v...
The paper proposes a new self‑supervised approach for learning 3D geometry from unposed images by shifting the asymmetry from the input space to the 3D representation space. By excluding held‑out views only from the reconstructed scene while using a shared backbone for all views, the method improves depth and pose estimation. It further leverages view density differences and aligns features with a frozen vision foundation model to provide additional geometric training signals without requiring annotations.
The paper introduces a framework for instruction‑guided 3D editing that does not require paired 3D supervision. It distills visual, semantic, and geometric knowledge from foundation models into a 3D editing model using a differentiable rendering pipeline, guided by a 2D visual prior from an image editing model and a semantic prior from a Vision‑Language Model. A 3D‑aware Distribution Matching regularization is added to prevent geometric collapse and ensure realistic 3D outputs, leading to superior instruction fidelity and cross‑view consistency compared to state‑of‑the‑art baselines.
arXiv:2607. 10762v1 Announce Type: cross Abstract: Cross-modal distillation from Vision Foundation Models (VFMs) to LiDAR backbones has recently emerged as a self-supervised pretraining strategy that reduces reliance on dense point-wise annotation for 3D scene understanding.
arXiv:2610.02597v1 Announce Type: new Abstract: Vision foundation models such as DINOv2, SigLIP2, and MASt3R develop complementary capabilities from different pretraining objectives, yet their knowle...
arXiv:2609.38177v1 Announce Type: cross Abstract: Reasoning about the 3D world from multi-view images remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While modern MLLMs...
The paper introduces SPAR3S, a sparse voxel‑aligned 3D latent generative model that completes 3D scenes from sparse, unconstrained multi‑view images. It learns a compact voxel‑aligned latent space using photometric supervision via differentiable 3D Gaussian Splatting, and employs a masked autoregressive transformer to predict missing voxel occupancy and latent tokens. Experiments on synthetic indoor scenes and RealEstate10k show that SPAR3S achieves higher novel‑view quality than prior methods and generalizes to real‑world data.
The paper introduces Poincar3, a self‑supervised method that learns multi‑view representations through self‑distillation rather than RGB reconstruction. By combining masked patch and image‑level distillation with a teacher that sees additional views, it trains from scratch without explicit 3D supervision. Poincar3 surpasses prior single‑ and multi‑view self‑supervised methods on tasks such as correspondence estimation, camera pose estimation, and 3D reconstruction, and its features encode camera motion more accurately thanks to a lightweight Poincaré adapter.
arXiv:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...
Spatial-OPSD is a label‑free self‑improvement framework for vision‑language models that leverages spatial priors such as depth, 3D relations, and camera geometry to provide dense token‑level supervision. During training, a privileged teacher uses these priors while the student learns from only the original visual‑language input, and a recursive round‑wise scheme allows repeated self‑improvement without moving the teacher. Across four VLM families, one round of Spatial‑OPSD improves the five‑benchmark average, and three rounds push a strong spatially specialized model to the open‑source frontier, achieving the highest average among open models and best results on three of five spatial reasoning benchmarks.
arXiv:2609.23796v1 Announce Type: new Abstract: Single-image 3D object generation can now produce high-fidelity assets, yet accurately placing them into a coherent scene layout remains an open challe...