Related papers: TransformerFusion: Monocular RGB Scene Reconstruct…

We present a method for relighting 3D reconstructions of large room-scale environments. Existing solutions for 3D scene relighting often require solving under-determined or ill-conditioned inverse rendering problems, and are as such unable…

3D reconstruction from a single 2D image was extensively covered in the literature but relies on depth supervision at training time, which limits its applicability. To relax the dependence to depth we propose SceneRF, a self-supervised…

Multi-sensor modal fusion has demonstrated strong advantages in 3D object detection tasks. However, existing methods that fuse multi-modal features require transforming features into the bird's eye view space and may lose certain…

Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…

Mobile robots operating indoors must be prepared to navigate challenging scenes that contain transparent surfaces. This paper proposes a novel method for the fusion of acoustic and visual sensing modalities through implicit neural…

Recent unified image generation models have achieved remarkable success by employing MLLMs for semantic understanding and diffusion backbones for image generation. However, these models remain fundamentally limited in spatially-aware tasks…

Enabling Large Language Models (LLMs) to interact with 3D environments is challenging. Existing approaches extract point clouds either from ground truth (GT) geometry or 3D scenes reconstructed by auxiliary models. Text-image aligned 2D…

While CNN-based methods have been the cornerstone of medical image segmentation due to their promising performance and robustness, they suffer from limitations in capturing long-range dependencies. Transformer-based approaches are currently…

The efficient fusion of depth maps is a key part of most state-of-the-art 3D reconstruction methods. Besides requiring high accuracy, these depth fusion methods need to be scalable and real-time capable. To this end, we present a novel…

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…

Although Convolutional Neural Networks (CNN) have made good progress in image restoration, the intrinsic equivalence and locality of convolutions still constrain further improvements in image quality. Recent vision transformer and…

We present a learning-based framework, recurrent transformer network (RTN), to restore heavily degraded old films. Instead of performing frame-wise restoration, our method is based on the hidden knowledge learned from adjacent frames that…

Surface material recognition is a key component in robotic perception and physical interaction, particularly when leveraging both tactile and visual sensory inputs. In this work, we propose Surformer v1, a transformer-based architecture…

Human perceive the 3D world through 2D observations from limited viewpoints. While recent feed-forward generalizable 3D reconstruction models excel at recovering 3D structures from sparse images, their representations are often confined to…

The end-to-end image fusion framework has achieved promising performance, with dedicated convolutional networks aggregating the multi-modal local appearance. However, long-range dependencies are directly neglected in existing CNN fusion…

Object-oriented maps are important for scene understanding since they jointly capture geometry and semantics, allow individual instantiation and meaningful reasoning about objects. We introduce FroDO, a method for accurate 3D reconstruction…

We present a novel online depth map fusion approach that learns depth map aggregation in a latent feature space. While previous fusion methods use an explicit scene representation like signed distance functions (SDFs), we propose a learned…

Light field cameras have been proved to be powerful tools for 3D reconstruction and virtual reality applications. However, the limited resolution of light field images brings a lot of difficulties for further information display and…

Reconstructing dynamic humans together with static scenes from monocular videos remains difficult, especially under fast motion, where RGB frames suffer from motion blur. Event cameras exhibit distinct advantages, e.g., microsecond temporal…

Despite significant progress in 3D object detection, point clouds remain challenging due to sparse data, incomplete structures, and limited semantic information. Capturing contextual relationships between distant objects presents additional…