PulseAugur
EN
LIVE 18:44:48

New AI Models Advance 3D Shape Completion and Depth Estimation

By PulseAugur Editorial · [7 sources] ·

Researchers have introduced several new models for 3D shape completion and depth estimation. The Large Depth Completion Model (LDCM) uses a transformer to generate dense depth maps from sparse observations, outperforming existing methods. I2PRef offers an image-driven approach to point cloud completion, reconstructing complete point clouds from single RGB images. DinoComplete leverages distilled semantic priors from DINO features and state space models for efficient and robust 3D shape completion, showing improved quality with fewer parameters. Additionally, ESSC-RM is a plug-and-play framework that refines existing Semantic Scene Completion models to enhance prediction performance. AI

IMPACT These advancements in 3D shape completion and depth estimation could enhance applications in robotics, augmented reality, and autonomous systems by improving scene understanding from limited data.

RANK_REASON Multiple research papers released on arXiv detailing new models and frameworks for 3D computer vision tasks.

Read on arXiv cs.CV →

AI-generated summary · Google Gemini · from 7 sources. How we write summaries →

New AI Models Advance 3D Shape Completion and Depth Estimation

COVERAGE [7]

  1. arXiv cs.CV TIER_1 English(EN) · Zhu Yu, Zhengyi Zhao, Runmin Zhang, Lingteng Qiu, Kejie Qiu, Yisheng He, Siyu Zhu, Zilong Dong, Si-Yuan Cao, Hui-Liang Shen ·

    Large Depth Completion Model from Sparse Observations

    arXiv:2605.30115v1 Announce Type: new Abstract: This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates…

  2. arXiv cs.CV TIER_1 English(EN) · Hui-Liang Shen ·

    Large Depth Completion Model from Sparse Observations

    This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates metric-accurate dense depth maps using a transf…

  3. arXiv cs.CV TIER_1 English(EN) · Azhar Hussian, Marina Ritthaler, Andr\'e Kaup, Vasileios Belagiannis ·

    I2PRef: Image-Driven Point Completion with Iterative Refinement

    arXiv:2605.26914v1 Announce Type: new Abstract: We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete…

  4. arXiv cs.CV TIER_1 English(EN) · Furkan Mert Algan, Eckehard Steinbach ·

    DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

    arXiv:2605.26949v1 Announce Type: new Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic…

  5. arXiv cs.CV TIER_1 English(EN) · Eckehard Steinbach ·

    DinoComplete: 3D Shape Completion with Distilled Semantic Priors and State Space Models

    3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic and efficient shape completion framework that a…

  6. arXiv cs.CV TIER_1 English(EN) · Vasileios Belagiannis ·

    I2PRef: Image-Driven Point Completion with Iterative Refinement

    We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, …

  7. arXiv cs.CV TIER_1 English(EN) · Dunxing Zhang (Technical University of Munich, Munich, Germany), Jiachen Lu (Technical University of Munich, Munich, Germany), Han Yang (National Science Center for Earthquake Engineering, Tianjin University, Tianjin, China, School of Civil Engineering, … ·

    Enhancing 3D Semantic Scene Completion with a Refinement Module

    arXiv:2512.18363v2 Announce Type: replace Abstract: We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network …

RELATED ENTITIES

RELATED TOPICS