no code implementations • 24 Jan 2024 • Daniel Lichy, Hang Su, Abhishek Badki, Jan Kautz, Orazio Gallo
Unfortunately, most of the GT data is for pinhole cameras, making it impossible to properly train depth estimation models for large-FoV cameras.
1 code implementation • CVPR 2023 • Jiashun Wang, Xueting Li, Sifei Liu, Shalini De Mello, Orazio Gallo, Xiaolong Wang, Jan Kautz
We present a zero-shot approach that requires only the widely available deformed non-stylized avatars in training, and deforms stylized characters of significantly different shapes at inference.
no code implementations • 5 May 2023 • Ekta Prashnani, Koki Nagano, Shalini De Mello, David Luebke, Orazio Gallo
This allows us to link the synthetic video to the identity driving the expressions in the video, regardless of the facial appearance shown.
1 code implementation • CVPR 2022 • Atsuhiro Noguchi, Umar Iqbal, Jonathan Tremblay, Tatsuya Harada, Orazio Gallo
Rendering articulated objects while controlling their poses is critical to applications such as virtual reality or animation for movies.
2 code implementations • CVPR 2022 • Eric R. Chan, Connor Z. Lin, Matthew A. Chan, Koki Nagano, Boxiao Pan, Shalini De Mello, Orazio Gallo, Leonidas Guibas, Jonathan Tremblay, Sameh Khamis, Tero Karras, Gordon Wetzstein
Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge.
no code implementations • 12 May 2021 • Chaoyang Wang, Ben Eckart, Simon Lucey, Orazio Gallo
Recent approaches to render photorealistic views from a limited set of photographs have pushed the boundaries of our interactions with pictures of static scenes.
1 code implementation • 16 Apr 2021 • Ekta Prashnani, Orazio Gallo, Joohwan Kim, Josef Spjut, Pradeep Sen, Iuri Frosio
We note that the accuracy of the maps reconstructed from the gaze data of a fixed number of observers varies with the frame, as it depends on the content of the scene.
1 code implementation • CVPR 2021 • Abhishek Badki, Orazio Gallo, Jan Kautz, Pradeep Sen
Time-to-contact (TTC), the time for an object to collide with the observer's plane, is a powerful tool for path planning: it is potentially more informative than the depth, velocity, and acceleration of objects in the scene -- even for humans.
1 code implementation • NeurIPS 2020 • Tewodros Habtegebrial, Varun Jampani, Orazio Gallo, Didier Stricker
We propose to push the envelope further, and introduce Generative View Synthesis (GVS), which can synthesize multiple photorealistic views of a scene given a single semantic map.
1 code implementation • CVPR 2020 • Abhishek Badki, Alejandro Troccoli, Kihwan Kim, Jan Kautz, Pradeep Sen, Orazio Gallo
Given a strict time budget, Bi3D can detect objects closer than a given distance in as little as a few milliseconds, or estimate depth with arbitrarily coarse quantization, with complexity linear with the number of quantization levels.
no code implementations • CVPR 2020 • Jae Shin Yoon, Kihwan Kim, Orazio Gallo, Hyun Soo Park, Jan Kautz
Our insight is that although its scale and quality are inconsistent with other views, the depth estimation from a single view can be used to reason about the globally coherent geometry of dynamic contents.
1 code implementation • CVPR 2020 • Abhishek Badki, Orazio Gallo, Jan Kautz, Pradeep Sen
Meshlets act as a dictionary of local features and thus allow to use learned priors to reconstruct object meshes in any pose and from unseen classes, even when the noise is large and the samples sparse.
no code implementations • 31 Jul 2019 • Wei-Sheng Lai, Orazio Gallo, Jinwei Gu, Deqing Sun, Ming-Hsuan Yang, Jan Kautz
Despite the long history of image and video stitching research, existing academic and commercial solutions still produce strong artifacts.
2 code implementations • CVPR 2019 • Hang Su, Varun Jampani, Deqing Sun, Orazio Gallo, Erik Learned-Miller, Jan Kautz
In addition, we also demonstrate that PAC can be used as a drop-in replacement for convolution layers in pre-trained networks, resulting in consistent performance improvements.
1 code implementation • ICCV 2019 • Inchang Choi, Orazio Gallo, Alejandro Troccoli, Min H. Kim, Jan Kautz
We present Extreme View Synthesis, a solution for novel view extrapolation that works even when the number of input images is small--as few as two.
2 code implementations • 23 Oct 2018 • Zhile Ren, Orazio Gallo, Deqing Sun, Ming-Hsuan Yang, Erik B. Sudderth, Jan Kautz
To date, top-performing optical flow estimation methods only take pairs of consecutive frames into account.
no code implementations • ECCV 2018 • Qi Guo, Iuri Frosio, Orazio Gallo, Todd Zickler, Jan Kautz
Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras.
no code implementations • 16 Jan 2018 • Huaijin Chen, Jinwei Gu, Orazio Gallo, Ming-Yu Liu, Ashok Veeraraghavan, Jan Kautz
Motion blur is a fundamental problem in computer vision as it impacts image quality and hinders inference.
no code implementations • ECCV 2018 • Patrick Wieschollek, Orazio Gallo, Jinwei Gu, Jan Kautz
The reflections caused by common semi-reflectors, such as glass windows, can impact the performance of computer vision algorithms.
no code implementations • 3 Dec 2016 • Suren Jayasuriya, Orazio Gallo, Jinwei Gu, Jan Kautz
Power consumption is a critical factor for the deployment of embedded computer vision systems.
2 code implementations • 28 Nov 2015 • Hang Zhao, Orazio Gallo, Iuri Frosio, Jan Kautz
Neural networks are becoming central in several areas of computer vision and image processing and different architectures have been proposed to solve specific problems.
no code implementations • 7 Apr 2015 • Orazio Gallo, Alejandro Troccoli, Jun Hu, Kari Pulli, Jan Kautz
Image registration for stack-based HDR photography is challenging.
1 code implementation • CVPR 2013 • Jun Hu, Orazio Gallo, Kari Pulli, Xiaobai Sun
We present a novel method for aligning images in an HDR (high-dynamic-range) image stack to produce a new exposure stack where all the images are aligned and appear as if they were taken simultaneously, even in the case of highly dynamic scenes.