Yu Zheng

Yu Zheng

Auto-generated profile, based on publicly available information

Yu Zheng

Department of Automation, Tsinghua University, Beijing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2020
Verified
Book Chapter
Closed access
PDF file
YZYu Zheng
Yu Zheng
DZDanyang Zhang
Danyang Zhang
SXSinan Xie
Sinan Xie
JLJiwen Lu
Jiwen Lu
JZJie Zhou
Jie Zhou

28 November 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YZYu Zheng
Yu Zheng
YDYueqi Duan
Yueqi Duan
ZLZongtai Li
Zongtai Li
JZJie Zhou
Jie Zhou
JLJiwen Lu
Jiwen Lu
In this paper, we propose a dynamic 3D object detector named HyperDet3D, which is adaptively adjusted based on the hyper scene-level knowledge on the fly. Existing methods strive for object-level representations of local elements and their relations without scene-level priors, which suffer from ambiguity between similarly-structured objects only based on the understanding of individual points and object candidates. Instead, we design scene-conditioned hypernetworks to simultaneously learn scene-agnostic embeddings to exploit sharable abstracts from various 3D scenes, and scene-specific knowledge which adapts the 3D detector to the given scene at test time. As a result, the lower-level ambiguity in object representations can be addressed by hierarchical context in scene priors. However, since the upstream hypernetwork in HyperDet3D takes raw scenes as input which contain noises and redundancy, it leads to sub-optimal parameters produced for the 3D detector simply under the constraint of downstream detection losses. Based on the fact that the downstream 3D detection task can be factorized into object-level semantic classification and bounding box regression, we furtherly propose HyperFormer3D by correspondingly designing their scene-level prior tasks in upstream hypernetworks, namely Semantic Occurrence and Objectness Localization . To this end, we design a transformer-based hypernetwork that translates the task-oriented scene priors into parameters of the downstream detector, which refrains from noises and redundancy of the scenes. Extensive experimental results on the ScanNet, SUN RGB-D and MatterPort3D datasets demonstrate the effectiveness of the proposed methods.

1 May 2020 in Journal of Policy Modeling
Verified
Journal Article
Closed access
AGAlexandre Gohin
Alexandre Gohin
YZYu Zheng
Yu Zheng

6 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
YZYu Zheng
Yu Zheng
HYHongru Yan
Hongru Yan
YDYueqi Duan
Yueqi Duan
JLJiwen Lu
Jiwen Lu
Inherently equipped with arbitrary resolution and multi-view consistency, the Neural Radiance Field (NeRF) as an implicit scene representation has drawn extensive attention. While traditional NeRFs excel at novel view synthesis (NVS) under ideal conditions, they overlook the potential of learning consistent geometric representations across varying sight qualities. Current methods mainly focus on optimizing synthesis under clear visibility, which limits their effectiveness in downstream scene understanding tasks where robust geometry comprehension is crucial. In this paper, we propose a NVS pre-training technique named ShadowNeRF which firstly synthesizes degraded views with shadowed regions to challenge the model in inferring complete scene geometries. We then design a self-supervised sight recovery process with a two-stage unshadowing framework, which progressively recovers neighboring areas and reveals geometric properties of invisible regions. This pre-training strategy of degradation synthesis and recovery, when combined with taskspecific fine-tuning, enhances the understanding of underlying scene structure for the model and strengthens its ability to process scenes under varying sight conditions. Through extensive experiments, we demonstrate that our pre-training and finetuning pipeline significantly improves the model performances in semantic segmentation and 3D object detection, as well as the reconstruction quality of complex scenes.

1 January 2026 in IEEE Transactions on Multimedia
Verified
Journal Article
Closed access
FKFanye Kong
Fanye Kong
HXHongyu Xia
Hongyu Xia
YZYu Zheng
Yu Zheng
BGBoyang Gong
Boyang Gong
JZJie Zhou
Jie Zhou
JLJiwen Lu
Jiwen Lu

19 October 2026 in Pattern Recognition
Verified
Journal Article
Closed access
FKFanye Kong
Fanye Kong
YZYu Zheng
Yu Zheng
LCLei Chen
Lei Chen
JZJie Zhou
Jie Zhou
JLJiwen Lu
Jiwen Lu