相关论文: SimpleProc: Fully Procedural Synthetic Data from S…

We present a modern solution to the multi-view photometric stereo problem (MVPS). Our work suitably exploits the image formation model in a MVPS experimental setup to recover the dense 3D reconstruction of an object from images. We procure…

Fine-tuning large-scale text-to-video diffusion models to add new generative controls, such as those over physical camera parameters (e.g., shutter speed or aperture), typically requires vast, high-fidelity datasets that are difficult to…

Image generative models have become indispensable tools to yield exquisite high-resolution (HR) images for everyone, ranging from general users to professional designers. However, a desired outcome often requires generating a large number…

Multi-view image acquisition systems with two or more cameras can be rather costly due to the number of high resolution image sensors that are required. Recently, it has been shown that by covering a low resolution sensor with a non-regular…

This paper tackles a challenging problem of generating photorealistic images from semantic layouts in few-shot scenarios where annotated training pairs are hardly available but pixel-wise annotation is quite costly. We present a training…

Learned visual compression is an important and active task in multimedia. Existing approaches have explored various CNN- and Transformer-based designs to model content distribution and eliminate redundancy, where balancing efficacy (i.e.,…

Quality control of assembly processes is essential in manufacturing to ensure not only the quality of individual components but also their proper integration into the final product. To assist in this matter, automated assembly control using…

Recent sparse multi-view scene reconstruction advances like DUSt3R and MASt3R no longer require camera calibration and camera pose estimation. However, they only process a pair of views at a time to infer pixel-aligned pointmaps. When…

This work aims to address the multi-view perspective RGB generation from text prompts given Bird-Eye-View(BEV) semantics. Unlike prior methods that neglect layout consistency, lack the ability to handle detailed text prompts, or are…

Single-image novel view synthesis is a challenging and ongoing problem that aims to generate an infinite number of consistent views from a single input image. Although significant efforts have been made to advance the quality of generated…

Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular depth estimation. However, in practice, the quality and…

Controllable synthetic data generation can substantially lower the annotation cost of training data. Prior works use diffusion models to generate driving images conditioned on the 3D object layout. However, those models are trained on…

Despite the significant progress in diffusion prior-based image restoration, most existing methods apply uniform processing to the entire image, lacking the capability to perform region-customized image restoration according to user…

Deep learning has recently demonstrated its excellent performance for multi-view stereo (MVS). However, one major limitation of current learned MVS approaches is the scalability: the memory-consuming cost volume regularization makes the…

Soft random sampling (SRS) is a simple yet effective approach for efficient training of large-scale deep neural networks when dealing with massive data. SRS selects a subset uniformly at random with replacement from the full data set in…

Prompt-based learning has shown considerable promise in reformulating various downstream tasks as cloze problems by combining original input with a predetermined template. This approach demonstrates its effectiveness, especially in few-shot…

Single-view novel view synthesis (NVS) is a notorious problem due to its ill-posed nature, and often requires large, computationally expensive approaches to produce tangible results. In this paper, we propose CheapNVS: a fully end-to-end…

The success of multi-modal large language models (MLLMs) has been largely attributed to the large-scale training data. However, the training data of many MLLMs is unavailable due to privacy concerns. The expensive and labor-intensive…

Videos show continuous events, yet most $-$ if not all $-$ video synthesis frameworks treat them discretely in time. In this work, we think of videos of what they should be $-$ time-continuous signals, and extend the paradigm of neural…

Single-view depth prediction is a fundamental problem in computer vision. Recently, deep learning methods have led to significant progress, but such methods are limited by the available training data. Current datasets based on 3D sensors…