Related papers: SimpleProc: Fully Procedural Synthetic Data from S…

Synthesizing high-fidelity videos from real-world multi-view input is challenging because of the complexities of real-world environments and highly dynamic motions. Previous works based on neural radiance fields have demonstrated…

Maximally parallel multiset rewriting systems (MPMRS) give a convenient way to express relations between unstructured objects. The functioning of various computational devices may be expressed in terms of MPMRS (e.g., register machines and…

Medical Vision-Language Pre-training (MedVLP) has made significant progress in enabling zero-shot tasks for medical image understanding. However, training MedVLP models typically requires large-scale datasets with paired, high-quality…

In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasible. Therefore, we…

Traditional multi-view stereo (MVS) methods rely heavily on photometric and geometric consistency constraints, but newer machine learning-based MVS methods check geometric consistency across multiple source views only as a post-processing…

Deep multi-view stereo (MVS) methods have been developed and extensively compared on simple datasets, where they now outperform classical approaches. In this paper, we ask whether the conclusions reached in controlled scenarios are still…

Recent advances in robot imitation learning have yielded powerful visuomotor policies capable of manipulating a wide variety of objects directly from monocular visual inputs. However, monocular observations inherently lack reliable depth…

State-of-the-art RGB texture synthesis algorithms rely on style distances that are computed through statistics of deep features. These deep features are extracted by classification neural networks that have been trained on large datasets of…

Offline reinforcement learning (RL) offers a promising framework for training agents using pre-collected datasets without the need for further environment interaction. However, policies trained on offline data often struggle to generalise…

Recent months have witnessed rapid progress in 3D generation based on diffusion models. Most advances require fine-tuning existing 2D Stable Diffsuions into multi-view settings or tedious distilling operations and hence fall short of 3D…

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any…

This paper describes a novel approach for on demand volumetric texture synthesis based on a deep learning framework that allows for the generation of high quality 3D data at interactive rates. Based on a few example images of textures, a…

BlenderProc is a modular procedural pipeline, which helps in generating real looking images for the training of convolutional neural networks. These can be used in a variety of use cases including segmentation, depth, normal and pose…

Novel view synthesis (NVS) is a challenging task in computer vision that involves synthesizing new views of a scene from a limited set of input images. Neural Radiance Fields (NeRF) have emerged as a powerful approach to address this…

Recent advances in multimodal learning have achieved remarkable success across diverse vision-language tasks. However, such progress heavily relies on large-scale image-text datasets, making training costly and inefficient. Prior efforts in…

This paper proposes a network, referred to as MVSTR, for Multi-View Stereo (MVS). It is built upon Transformer and is capable of extracting dense features with global context and 3D consistency, which are crucial to achieving reliable…

We present a novel neural radiance model that is trainable in a self-supervised manner for novel-view synthesis of dynamic unstructured scenes. Our end-to-end trainable algorithm learns highly complex, real-world static scenes within…

Neural Radiance Fields (NeRF) show impressive performance for the photorealistic free-view rendering of scenes. However, NeRFs require dense sampling of images in the given scene, and their performance degrades significantly when only a…

Despite the rapid advancements in Multimodal Large Language Models (MLLMs), a critical question regarding their visual grounding mechanism remains unanswered: do these models genuinely ``read'' text embedded in images, or do they merely…

In this paper, we propose a novel end-to-end deep neural network model for omnidirectional depth estimation from a wide-baseline multi-view stereo setup. The images captured with ultra wide field-of-view (FOV) cameras on an omnidirectional…