Search Results for author:
Found 32 papers, 13 papers with code
HDRFlow: Real-Time HDR Video Reconstruction with Large Motions
HDRFlow has three novel designs: an HDR-domain alignment loss (HALoss), an efficient flow network with a multi-size large kernel (MLK), and a new HDR flow training scheme.
GenNBV: Generalizable Next-Best-View Policy for Active 3D Reconstruction
Previous works attempt to automate this process using the Next-Best-View (NBV) policy for active 3D reconstruction.
Event-Based Motion Magnification
Detecting and magnifying imperceptible high-frequency motions in real-world scenarios has substantial implications for industrial and medical applications.
EmbodiedScan: A Holistic Multi-Modal 3D Perception Suite Towards Embodied AI
In the realm of computer vision and robotics, embodied agents are expected to explore their environment and carry out human instructions.
Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models
We introduce a Depicted image Quality Assessment method (DepictQA), overcoming the constraints of traditional score-based methods.
Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors
Recently, researchers have attempted to improve the genuineness of 3D objects by directly training on 3D datasets, albeit at the cost of low-quality texture generation due to the limited texture diversity in 3D datasets.
Obj-NeRF: Extract Object NeRFs from Multi-view Images
To solve this problem, in this paper, we propose Obj-NeRF, a comprehensive pipeline that recovers the 3D geometry of a specific object from multi-view images using a single prompt.
AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion
To this end, we propose an all-in-one image restoration framework with latent diffusion (AutoDIR), which can automatically detect and address multiple unknown degradations.
Reconstruct-and-Generate Diffusion Model for Detail-Preserving Image Denoising
To address the trade-off between visual appeal and fidelity of high-frequency details in denoising tasks, we propose a novel approach called the Reconstruct-and-Generate Diffusion Model (RnG).
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
Neural Radiance Fields (NeRFs) are a powerful representation for modeling a 3D scene as a continuous function.
Fast and High-Quality Image Denoising via Malleable Convolutions
These spatially-varying kernels are produced by an efficient predictor network running on a downsampled input, making them much more efficient to compute than per-pixel kernels produced by a full-resolution image, and also enlarging the network's receptive field compared with static kernels.
Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image
We use data captured with a consumer smartphone camera to demonstrate that, after a one-time calibration step, our approach improves upon prior works for both defocus map estimation and blur removal, despite being entirely unsupervised.
How to Train Neural Networks for Flare Removal
When a camera is pointed at a strong light source, the resulting photograph may contain lens flare artifacts.
Real-time Localized Photorealistic Video Style Transfer
We present a novel algorithm for transferring artistic styles of semantically meaningful local regions of an image onto local regions of a target video while preserving its photorealism.
Learned Dual-View Reflection Removal
Traditional reflection removal algorithms either use a single image as input, which suffers from intrinsic ambiguities, or use multiple images from a moving camera, which is inconvenient for users.
Neural Light Transport for Relighting and View Synthesis
In particular, we show how to fuse previously seen observations of illuminants and views to synthesize a new image of the same scene under a desired lighting condition from a chosen viewpoint.
Joint Bilateral Learning for Real-time Universal Photorealistic Style Transfer
Photorealistic style transfer is the task of transferring the artistic style of an image onto a content target, producing a result that is plausibly taken with a camera.
Handheld Mobile Photography in Very Low Light
Aside from the physical limits imposed by read noise and photon shot noise, these cameras are typically handheld, have small apertures and sensors, use mass-produced analog electronics that cannot easily be cooled, and are commonly used to photograph subjects that move, like children and pets.
Stereoscopic Dark Flash for Low-light Photography
In this work, we present a camera configuration for acquiring "stereoscopic dark flash" images: a simultaneous stereo pair in which one camera is a conventional RGB sensor, but the other camera is sensitive to near-infrared and near-ultraviolet instead of R and B.
Unprocessing Images for Learned Raw Denoising
Machine learning techniques work best when the data used for training resembles the data used for evaluation.
Ranked #1 on
Color Image Denoising
on Darmstadt Noise Dataset
MoSculp: Interactive Visualization of Shape and Time
We present a system that allows users to visualize complex human motion via 3D motion sculptures---a representation that conveys the 3D structure swept by a human body as it moves through space.
Seeing Tree Structure from Vibration
Humans recognize object structure from both their appearance and motion; often, motion helps to resolve ambiguities in object structure that arise when we observe object appearance only.
Visual Dynamics: Stochastic Future Generation via Layered Cross Convolutional Networks
We study the problem of synthesizing a number of likely future frames from a single input image.
Pix3D: Dataset and Methods for Single-Image 3D Shape Modeling
We study 3D shape modeling from a single image and make contributions to it in three aspects.
Ranked #1 on
3D Shape Classification
on Pix3D
3D Interpreter Networks for Viewer-Centered Wireframe Modeling
3D-INN is trained on real images to estimate 2D keypoint heatmaps from an input image; it then predicts 3D object structure from heatmaps using knowledge learned from synthetic 3D shapes.
Video Enhancement with Task-Oriented Flow
Many video enhancement algorithms rely on optical flow to register frames in a video sequence.
Ranked #7 on
Video Frame Interpolation
on Middlebury
MarrNet: 3D Shape Reconstruction via 2.5D Sketches
First, compared to full 3D shape, 2. 5D sketches are much easier to be recovered from a 2D image; models that recover 2. 5D sketches are also more likely to transfer from synthetic to real data.
Ranked #2 on
3D Shape Classification
on Pix3D
3D Object Reconstruction From A Single Image
3D Reconstruction
+3
Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling
We study the problem of 3D object generation.
Ranked #3 on
3D Shape Classification
on Pix3D
3D Object Recognition
3D Point Cloud Linear Classification
+3
Best-Buddies Similarity - Robust Template Matching using Mutual Nearest Neighbors
We propose a novel method for template matching in unconstrained environments.
Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks
We study the problem of synthesizing a number of likely future frames from a single input image.
Single Image 3D Interpreter Network
In this work, we propose 3D INterpreter Network (3D-INN), an end-to-end framework which sequentially estimates 2D keypoint heatmaps and 3D object structure, trained on both real 2D-annotated images and synthetic 3D data.
The Aperture Problem for Refractive Motion
We pose and solve a generalization of the aperture problem for moving refractive elements.
