Related papers: On the Design and Analysis of Multiple View Descri…
Neural Radiance Fields (NeRF) have garnered considerable attention as a paradigm for novel view synthesis by learning scene representations from discrete observations. Nevertheless, NeRF exhibit pronounced performance degradation when…
We investigate what structure emerges in 3D Gaussian Splatting (3DGS) solutions from standard multi-view optimization. We term these Rendering-Optimal References (RORs) and analyze their statistical properties, revealing stable patterns:…
Visualization techniques for the decision space of continuous multi-objective optimization problems (MOPs) are rather scarce in research. For long, all techniques focused on global optimality and even for the few available landscape…
Hashing techniques have been applied broadly in retrieval tasks due to their low storage requirements and high speed of processing. Many hashing methods based on a single view have been extensively studied for information retrieval.…
A new thresholding strategy for the estimation of a deterministic image immersed in noise is introduced. The threshold is combined with a wavelet decomposition, where the wavelet coefficient of the image at any fixed value of the…
This paper studies the problem of view synthesis with certain amount of rotations from a pair of images, what we called stereo unstructured magnification. While the multi-plane image representation is well suited for view synthesis with…
We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model. Specifically, we introduce a Holistic Scene Grammar (HSG)…
We present a unified framework for studying the identifiability of representations learned from simultaneously observed views, such as different data modalities. We allow a partially observed setting in which each view constitutes a…
We propose the ambiguity problem for the foreground object segmentation task and motivate the importance of estimating and accounting for this ambiguity when designing vision systems. Specifically, we distinguish between images which lead…
Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source…
Occupancy prediction infers fine-grained 3D geometry and semantics from camera images of the surrounding environment, making it a critical perception task for autonomous driving. Existing methods either adopt dense grids as scene…
With the aim to improve the performance of feature matching, we present an unsupervised approach to fuse various local descriptors in the space of homographies. Inspired by the observation that the homographies of correct feature…
Generating human-object interactions (HOIs) is critical with the tremendous advances of digital avatars. Existing datasets are typically limited to humans interacting with a single object while neglecting the ubiquitous manipulation of…
Variational approaches to disparity estimation typically use a linearised brightness constancy constraint, which only applies in smooth regions and over small distances. Accordingly, current variational approaches rely on a schedule to…
Estimation of density functions supported on general domains arises when the data is naturally restricted to a proper subset of the real space. This problem is complicated by typically intractable normalizing constants. Score matching…
In physics, density $\rho(\cdot)$ is a fundamentally important scalar function to model, since it describes a scalar field or a probability density function that governs a physical process. Modeling $\rho(\cdot)$ typically scales poorly…
Human-object interaction (HOI) detection requires a large amount of annotated data. Current algorithms suffer from insufficient training samples and category imbalance within datasets. To increase data efficiency, in this paper, we propose…
We introduce MultiDiff, a novel approach for consistent novel view synthesis of scenes from a single RGB image. The task of synthesizing novel views from a single reference image is highly ill-posed by nature, as there exist multiple,…
We propose a self-supervised training approach for learning view-invariant dense visual descriptors using image augmentations. Unlike existing works, which often require complex datasets, such as registered RGBD sequences, we train on an…
The rapid growth of 3D Gaussian Splatting (3DGS) has revolutionized neural rendering, enabling real-time production of high-quality renderings. However, the previous 3DGS-based methods have limitations in urban scenes due to reliance on…