相关论文: Ray-Aware Pointer Memory with Adaptive Updates for…

Precise 6D pose estimation of rigid objects from RGB images is a critical but challenging task in robotics, augmented reality and human-computer interaction. To address this problem, we propose DeepRM, a novel recurrent network architecture…

In this paper we introduce a novel Depth-Aware Video Saliency approach to predict human focus of attention when viewing RGBD videos on regular 2D screens. We train a generative convolutional neural network which predicts a saliency map for…

We introduce the simple idea of adaptive view planning to multi-view synthesis, aiming to improve both occlusion revelation and 3D consistency for single-view 3D reconstruction. Instead of producing an unordered set of views independently…

In online continual learning, a neural network incrementally learns from a non-i.i.d. data stream. Nearly all online continual learning methods employ experience replay to simultaneously prevent catastrophic forgetting and underfitting on…

Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian…

We propose and evaluate a neural point-based graphics method that can model semi-transparent scene parts. Similarly to its predecessor pipeline, ours uses point clouds to model proxy geometry, and augments each point with a neural…

Contemporary deep neural networks offer state-of-the-art results when applied to visual reasoning, e.g., in the context of 3D point cloud data. Point clouds are important datatype for precise modeling of three-dimensional environments, but…

Research into dynamic 3D scene understanding has primarily focused on short-term change tracking from dense observations, while little attention has been paid to long-term changes with sparse observations. We address this gap with MoRE, a…

Recent trends in sparse-view 3D reconstruction have taken two different paths: feed-forward reconstruction that predicts pixel-aligned point maps without a complete geometry, and generative 3D reconstruction that generates complete geometry…

Point tracking aims to identify the same physical point across video frames and serves as a geometry-aware representation of motion. This representation supports a wide range of applications, from robotics to augmented reality, by enabling…

The majority of existing large 3D shape datasets contain meshes that lend themselves extremely well to visual applications such as rendering, yet tend to be topologically invalid (i.e, contain non-manifold edges and vertices, disconnected…

Modern machine learning systems need to be able to cope with constantly arriving and changing data. Two main areas of research dealing with such scenarios are continual learning and data stream mining. Continual learning focuses on…

The attention mechanism provides a sequential prediction framework for learning spatial models with enhanced implicit temporal consistency. In this work, we show a systematic design (from 2D to 3D) for how conventional networks and other…

World building with 3D scene representations is increasingly important for content creation, simulation, and interactive experiences, yet real workflows are inherently iterative: creators must repeatedly extend an existing scene under user…

This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive. This is in contrast to prior works that often rely on computationally heavy 3D convolutions, ignore actual motion when aligning…

In this paper, we propose an adaptive keyframe selection method for improved 3D scene reconstruction in dynamic environments. The proposed method integrates two complementary modules: an error-based selection module utilizing photometric…

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…

We introduce MapAnything, a unified transformer-based feed-forward model that ingests one or more images along with optional geometric inputs such as camera intrinsics, poses, depth, or partial reconstructions, and then directly regresses…

Modern Recurrent Neural Networks have become a competitive architecture for 3D reconstruction due to their linear-time complexity. However, their performance degrades significantly when applied beyond the training context length, revealing…

We address the problems of measuring geometric similarity between 3D scenes, represented through point clouds or range data frames, and associating them. Our approach leverages macro-scale 3D structural geometry - the relative configuration…