Search Results for author:
Found 28 papers, 13 papers with code
BurstM: Deep Burst Multi-scale SR using Fourier Space with Optical Flow
However, the existing MFSR suffers from misalignments between the reference and source frames due to the limitations of DCN, such as small receptive fields and the predefined number of kernels.
Ranked #1 on
Burst Image Super-Resolution
on BurstSR
Burst Image Super-Resolution
Multi-Frame Super-Resolution
+1
TEXTOC: Text-driven Object-Centric Style Transfer
It ensures a seamless and harmonious style transfer across object regions.
Flow4D: Leveraging 4D Voxel Network for LiDAR Scene Flow Estimation
In addition, Flow4D further improves performance by using five frames to take advantage of richer temporal information.
Context-Aware Video Instance Segmentation
In this paper, we introduce the Context-Aware Video Instance Segmentation (CAVIS), a novel framework designed to enhance instance association by integrating contextual information adjacent to each object.
Ranked #1 on
Video Instance Segmentation
on OVIS validation
(using extra training data)
JDEC: JPEG Decoding via Enhanced Continuous Cosine Coefficients
We propose a practical approach to JPEG image decoding, utilizing a local implicit neural representation with continuous cosine formulation.
Multi-task Learning for Real-time Autonomous Driving Leveraging Task-adaptive Attention Generator
Real-time processing is crucial in autonomous driving systems due to the imperative of instantaneous decision-making and rapid response.
Depth-discriminative Metric Learning for Monocular 3D Object Detection
Moreover, we introduce an auxiliary head for object-wise depth estimation, which enhances depth quality while maintaining the inference time.
Rethinking LiDAR Domain Generalization: Single Source as Multiple Density Domains
The DDFE module is meticulously designed to extract density-specific features within a single source domain, facilitating the recognition of objects sharing similar density characteristics across different LiDAR sensors.
Rotation Matters: Generalized Monocular 3D Object Detection for Various Camera Systems
In this paper, we conduct extensive experiments to analyze the factors that cause performance degradation.
Implicit Neural Image Stitching
Existing frameworks for image stitching often provide visually reasonable stitchings.
Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies
In this paper, we present a new MTL framework that searches for structures optimized for multiple tasks with diverse graph topologies and shares features among tasks.
Offline-to-Online Knowledge Distillation for Video Instance Segmentation
In this paper, we present offline-to-online knowledge distillation (OOKD) for video instance segmentation (VIS), which transfers a wealth of video knowledge from an offline model to an online model for consistent prediction.
A Study on the Generality of Neural Network Structures for Monocular Depth Estimation
In this paper, we deeply investigate the various backbone networks (e. g. CNN and Transformer models) toward the generalization of monocular depth estimation.
Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
In this paper, we investigate the backbone networks (e. g. CNNs, Transformers, and CNN-Transformer hybrid models) toward the generalization of monocular depth estimation.
ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
In this paper, we present a direct adaptation strategy (ADAS), which aims to directly adapt a single model to multiple target domains in a semantic segmentation task without pretrained domain-specific models.
Ranked #3 on
Domain Adaptation
on GTAV to Cityscapes+Mapillary
Facial Depth and Normal Estimation using Single Dual-Pixel Camera
Many mobile manufacturers recently have adopted Dual-Pixel (DP) sensors in their flagship models for faster auto-focus and aesthetic image captures.
ZeBRA: Precisely Destroying Neural Networks with Zero-Data Based Repeated Bit Flip Attack
Many prior works on adversarial weight attack require not only the weight parameters, but also the training or test dataset in searching vulnerable bits to be attacked.
VolumeFusion: Deep Depth Fusion for 3D Scene Reconstruction
To reconstruct a 3D scene from a set of calibrated views, traditional multi-view stereo techniques rely on two distinct stages: local depth maps computation and global depth maps fusion.
DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation
Our model encodes individual representations of content (scene structure) and style (artistic appearance) from both source and target images.
Ranked #1 on
Domain Adaptation
on MNIST-to-MNIST-M
Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.
Ranked #3 on
Monocular Depth Estimation
on Cityscapes
Instance-wise Depth and Motion Learning from Monocular Videos
We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision.
Learning Residual Flow as Dynamic Motion from Stereo Videos
Based on rigid projective geometry, the estimated stereo depth is used to guide the camera motion estimation, and the depth and camera motion are used to guide the residual flow estimation.
DPSNet: End-to-end Deep Plane Sweep Stereo
The cost volume is constructed using a differentiable warping process that allows for end-to-end training of the network.
Robust Depth Estimation from Auto Bracketed Images
As demand for advanced photographic applications on hand-held devices grows, these electronics require the capture of high quality depth.
Noise Robust Depth From Focus Using a Ring Difference Filter
With the result from the FM, the role of a DfF pipeline is to determine and recalculate unreliable measurements while enhancing those that are reliable.
High-Quality Depth From Uncalibrated Small Motion Clip
We propose a novel approach that generates a high-quality depth map from a set of images captured with a small viewpoint variation, namely small motion clip.
Stereo Matching With Color and Monochrome Cameras in Low-Light Conditions
Consumer devices with stereo cameras have become popular because of their low-cost depth sensing capability.
High Quality Structure From Small Motion for Rolling Shutter Cameras
To address these problems, we introduce a novel 3D reconstruction method from narrow-baseline image sequences that effectively handles the effects of a rolling shutter that occur from most of commercial digital cameras.
