The photograph depicts a research poster presentation at an academic conference. The poster, titled “Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching," authored by Peng Liu, Zhiyu Xiang, Chengyu Qiao, Jingyun Fu, and Tianyu Pu from Zhejiang University, is displayed on board number 29. The poster elaborates on advanced techniques in stereo matching, focusing on adaptive multi-modal probability modeling to address issues of object boundary blurring and alignment artifacts in reconstructed point clouds.

Key sections of the poster include:
1. **Motivation**: Highlighting the challenges in existing stereo matching networks and the aim of improving stereo ground-truth models and robustness.
2. **Contributions**: Detailing the introduction of a novel multi-modal probability model, a dominant modality estimator (DME), and the superior performance results on public benchmarks.
3. **Our Method**: Illustrated with diagrams, describing the technical approach in separating different models within the local window to achieve precise stereo matching.
4. **Quantitative Results & Generalization Performance**: Tables and charts providing performance metrics and qualitative results, demonstrating the efficacy of the proposed method.
5. **Visualization of Output Distribution**: Comparative imagery showing the improvements in output distributions against benchmarks.

In the background, attendees of the conference are seen engaging with the presenters and discussing the content. This scene captures the academic rigour and collaborative nature of such conferences, emphasizing the dissemination and discussion of cutting-edge research in computer vision and pattern recognition. The poster includes QR codes for accessing additional resources and links, underscoring the integration of digital tools for enhanced information sharing.
Text transcribed from the image:
CVPR
TMD SEATTLE, WA
128
Nbe. Inl. Runtime (ms)
024
124
24.0
007 CITY
浙江大學
HEJIANG
ZHEJIANG UNIVERSITY
Motivation
Stereo matching networks usually over-smoothly
estimate object boundaries, causing bleeding artifacts
in reconstructed point clouds.
21
Adaptive Multi-Modal Cross-Entropy Loss for Stereo Matching
Peng Xu Zhiyu Xiang Chengyu Qiao Jingyun Fu Tianyu Pu
Our Method
Clusteri
Laplacian Modeling for each Cluster Adaptive Multi-Modal Laplacian Modelling
TALCVPR
SEATTLE, WA JUNE 17-21, 2024
Quantitative Results
Method
田
20
POSE
230 405 258
208
3.48 2.36
367
ING 42
232
171
234
24t
154 433
234
120
8
Sachet
3.30
1
212
334 153
10
211
242
PSMMO-MOM
3.49 182
230
271
18
430
200
2.08
154
CON
1.56
320
131
130
Actes
270
251
3
129
➤ Existing methods model the disparity ground-truth as
the uni-modal distribution, but fail to suppress the
multi-modal outputs at the edge. Meanwhile, the
single-modal disparity estimator (SME) suffers from
severe misalignment artifacts.
Disparity Ground-Trath
First, clustering is applied within the local window to separate different modals.
Then, each cluster is modeled as a uni-modal distribution using the Laplacian distribution.
Last, structural information is used to fuse the generated distributions into a multi-modal distribution.
Qualitative Results
All of the three baselines are lifted to a highly competitive level by our method
GANet with our method achieves new state-of-the-art results on both (OTT) 2015
and KITTI 2012 benchmarks
GAN
233
234
148
346 1.5
AT
321
230
+19
157
126
2.54 145
=
ACVNE
10
165
2.36
EST
133
123 107
1.40
129 265
123
16
231
267
262
149
171
233
112 200
1.38
409
130
2.46
130
Gechet-
-Oun
142
160
130
GANGE-OUSS
1.38 2.38 155
124
154
16
253
14
the selection of SME
the selection of DME
➤ Our work aims to explore a better modeling for the
stereo ground-truth and improve the robustness of the
disparity estimator.
Contributions
An adaptive multi-modal probability modeling for
supervising stereo networks training, effectively guiding
the networks to learn clear distribution patterns.
A dominant-modal disparity estimator (DME) that can
obtain accurate results upon multi-modal outputs.
> State-of-the-art performance on both the KITTI 2015
and KITTI 2012 benchmarks.
➤ Excellent cross-domain generalization performance.
The output probability distribution
➤ We propose to select the modal with the
maximum cumulative probability as the
dominant modal.
Vis. of Output Distributions
Left image
PSMNet [1] PSMNet-12] PSMNet-Ours
Top row: background pixel
➤Bottom row: foreground pixel
Generalization Performance
Links
29
29
PSMNet [1]
PSMN-2
PSMNet-Ours
From top to bottom: left images, disparity maps, error maps, and
reconstructed point clouds
Let images
PSM
PS-Ou
From top to betham: KITT 2015, KITTI 2012, Middlebury, and ETH
References
[1] Chang and Chen. Pyramid stereo matching network, CPR 221
(2) Chen, Chen, and Cheng. On the over-smoothing problem of cm based disparty estimation, CC 2