MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Authors: Lejia Ye, Yuhua Xu, Yulan Guo, Lian Xu, Xiaohu Zhang
Organizations: the School of Aeronautics and Astronautics, Sun Yat-sen University, Shenzhen Campus, Shenzhen 518107, China · Orbbec Inc., Orbbec Technology Building, No. 88 High-tech North 1st Road, Nanshan District, Shenzhen 518052, China · the School of Electronics and Communication Engineering, Sun Yat-sen University, Shenzhen Campus, Shenzhen 518107, China · the Department of Computer Science and Software Engineering, The University of Western Australia, Perth, WA 6009, Australia
Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing methods often treat these surface types separately, limiting their generalizability and physical plausibility. To bridge this gap, we propose MicroSDF, a novel neural implicit framework that facilitates geometry and reflectance modeling through microfacet theory. Our approach incorporates three core innovations: (i) a microfacet-guided geometry model that extracts multi-scale surface normals (macroscopic and microfacet) from a signed distance field (SDF), regularized by a proposed microfacet normal consistency loss to enforce physically plausible surface orientations; (ii) an enhanced dual-branch color model, where the specular branch leverages the microfacet normals to model high-frequency reflectance, and the vanilla branch, unlike prior works, uses reflection direction (instead of viewing direction) to better model diffuse and low-frequency specular components; and (iii) a detection-guided color blending strategy that adaptively fuses the color outputs based on reflection priors, providing more physically intuitive blending than implicitly learned blending weights. Combined with a tailored multi-stage optimization scheme, the proposed MicroSDF achieves robust and high-fidelity reconstruction across reflective and non-reflective surfaces. Extensive experiments on DTU, Shiny Blender, Ref-NeRF, and DeepVoxels datasets demonstrate state-of-the-art performance, establishing a new direction for physically grounded neural reconstruction.
Figures & tables
Fig. 1: Comparison between prior works and ours for implicit 3D reconstruction. ( a ) Prior dual-branch color modeling methods [ 5 , 6 ] . ( b ) The proposed dual-branch color modeling method. Our approach differs from prior works in the following three aspects: ( i ) Using reflection direction d^ as input to the vanilla branch to better model diffuse and low-frequency specular reflections, ( ii ) leveraging microfacet normals as input to the specular branch to capture high-frequency specular highlights, and ( iii ) using detection-based weights for physically intuitive color blending. These designs lead to significantly better geometric reconstruction on complex reflective surfaces than prior works.
Fig. 2: Overview of the proposed MicroSDF. It comprises a geometry network ΘG and a color network ΘC . The geometry network samples spatial points x , encodes them via an instant Neural Graphics Primitive(iNGP) [ 66 ] to obtain features F , and passes these to the SDF MLP, which is initialized using the external point cloud P . The color network ΘC consists of Vanilla MLP and Specular MLP, both receiving the same inputs: geometric features F , points x , reflection direction d^ (computed from normal n and viewing direction d ), and normal n . The Specular MLP additionally takes microfacet normals m as input. The outputs from the two branches are fused via the proposed detection-guided blending module, where the blending weights are predicted by an additional specular detector, yielding the final color.
Fig. 3: Microfacet normal characteristics. p1 and p2 illustrate representative points on specular and diffuse surfaces, respectively. According to microfacet theory, the normal variance at specular surfaces ( p1 ) is smaller than that at diffuse surfaces ( p2 ).
Geometry Init.
1st Level
Coarse-to-Fine
Finest Level
Lsdf
✓
Lmask
✓
Lcolor
✓
✓
✓
Leik
✓
✓
✓
Lcurv
✓
✓
Lmicrofacet
✓
✓
TABLE I: Loss terms used at different training stages.
Fig. 4: Qualitative comparison results on the DTU benchmark. Our approach achieves reconstruction that preserves finer geometric details compared to the state-of-the-art neural implicit method, NeuS [ 3 ] , while significantly outperforming the general-purpose reconstruction method UniSDF [ 5 ] .
Fig. 5: Qualitative comparison of the reflective surface reconstruction between the state-of-the-art methods and ours on the DeepVoxels (top two scenes) and Ref-NeRF (bottom three scenes) datasets. Our method outperforms UniSDF [ 5 ] and AniSDF [ 6 ] with higher success rates and better geometric fidelity.
Methods
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
Runtime
VolSDF* [ 16 ]
1.14
1.26
0.81
0.49
1.25
0.70
0.72
1.29
1.18
0.70
0.66
1.08
0.42
0.61
0.55
0.86
≈8h
NeuS* [ 3 ]
1.37
1.21
0.73
0.40
1.20
0.70
0.72
1.01
1.16
0.82
0.66
1.69
0.39
0.49
0.51
0.87
≈8h
NeuralWarp* [ 72 ]
0.49
0.71
0.38
0.38
0.79
0.81
0.82
1.20
1.06
0.68
0.66
0.74
0.41
0.63
0.51
0.68
≈8h
Neuralangelo* [ 7 ]
0.49
1.05
0.95
0.38
1.22
1.10
2.16
1.68
1.78
0.93
0.44
1.46
0.41
1.13
0.97
1.08
≈16h
PermutoSDF* [ 73 ]
0.52
0.75
0.41
0.37
0.90
0.66
0.59
1.37
1.07
0.85
0.46
0.98
0.33
0.39
0.50
0.68
≈1h
UniSDF* [ 5 ]
0.54
0.84
0.66
0.51
0.76
0.64
0.71
0.70
0.86
0.57
0.69
0.65
0.45
0.56
0.50
0.64
≈1h
TABLE II: Reconstruction performance on the DTU dataset in terms of Chamfer distance(mm) ↓ (lower is better). Red and orange denote the best and the second-best results, respectively. Results marked with * are sourced from the UniSDF [ 5 ] paper, while others are reported from their respective papers.
Method
MAE ∘ ↓
ACC ↓
car
ball
helmet
teapot
toaster
coffee
mean
car
helmet
toaster
coffee
mean
Geo-NeuS* [ 18 ]
12.15
1.04
4.12
19.77
16.23
9.79
10.52
0.72
0.74
4.14
0.90
1.63
Neuralangelo* [ 7 ]
12.34
35.63
9.23
4.98
14.14
8.61
14.16
1.89
1.71
2.99
0.63
1.81
Ref-NeRF* [ 65 ]
14.93
1.55
29.48
9.23
42.87
12.24
18.38
–
–
–
–
–
NMF [ 64 ]
7.74
0.72
2.40
5.67
6.66
13.17
6.06
–
–
–
–
–
Ref-NeuS* [ 4 ]
7.68
0.50
1.94
10.25
5.95
5.73
5.34
0.50
0.53
0.54
1.83
0.85
TABLE III: Quantitative results on Shiny Blender dataset. Lower is better for both MAE ∘ and ACC. Red and orange denote the best and the second-best results, respectively. Results marked with * are sourced from the UniSDF [ 5 ] paper, while others are reported from their respective papers.
MS
RD
DC
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
×
✓
✓
0.95
0.62
0.32
0.51
0.92
0.58
0.52
1.37
1.01
0.51
0.50
0.69
0.35
0.43
0.39
0.65
✓
×
✓
0.74
0.75
0.35
0.54
0.84
0.70
0.58
1.33
0.99
0.50
0.50
0.68
0.34
0.41
0.39
0.64
✓
✓
×
0.60
0.73
0.31
0.53
0.89
0.51
0.52
1.35
0.92
0.50
0.47
0.75
0.38
0.37
0.39
0.615
✓
✓
✓
0.53
0.64
0.31
0.44
0.88
0.62
0.56
1.34
1.00
0.52
0.48
0.66
0.33
0.39
0.40
0.607
TABLE IV: Ablation on microfacet normals sampling (MS), reflective direction of Vanilla MLP (RD), and detection-based color blend weighting strategy (DC). All metrics are reported in Chamfer Distance (mm) ↓ (lower is better). Red and orange denote top and second-best results. When DC= × , blending weights are learned via MLP as in UniSDF [ 5 ] .
DC Config
MAE ∘ ↓
ACC ↓
car
ball
helmet
teapot
toaster
coffee
mean
car
helmet
toaster
coffee
mean
Stable
7.60
0.54
1.84
3.44
9.88
8.92
5.37
0.44
0.29
1.37
1.10
0.80
All Zeros
7.44
0.54
1.84
3.30
8.38
7.28
4.80
0.42
0.29
1.26
0.85
0.71
MLP
7.09
0.59
1.71
3.16
8.25
6.76
4.59
0.35
0.23
1.16
0.86
0.65
All Ones
7.15
0.51
1.77
3.60
7.92
6.55
4.58
0.35
0.24
0.90
0.94
0.61
TABLE V: Ablation study on detection-based color blending (DC) strategies on Shiny Blender dataset. Lower is better for both MAE ∘ and ACC. Red and orange denote the best and the second-best results, respectively. Stable : StableDelight detection scores; All Ones : all blending weights 1 (fully specular branch); All Zeros : all 0 (fully diffuse branch); MLP : weights learned via auxiliary MLP as in UniSDF [ 5 ] .
DC Config
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
All Ones
0.60
0.69
0.37
0.59
0.87
0.58
0.61
1.46
1.06
0.53
0.48
0.72
0.34
0.38
0.40
0.65
All Zeros
0.64
0.73
0.31
0.51
0.83
0.54
0.55
1.37
1.05
0.52
0.46
0.76
0.38
0.41
0.39
0.63
MLP
0.60
0.73
0.31
0.53
0.89
0.51
0.52
1.35
0.92
0.50
0.47
0.75
0.38
0.37
0.39
0.615
Stable
0.53
0.64
0.31
0.44
0.88
0.62
0.56
1.34
1.00
0.52
0.48
0.66
0.39
0.39
0.40
0.607
TABLE VI: Ablation study on detection-based color blending (DC) strategies on DTU dataset (Chamfer Distance (mm) ↓ , lower is better). Red and orange denote the best and second-best per column. Stable : StableDelight detection scores; All Ones : all blending weights set to 1 (fully using the specular branch); All Zeros : all blending weights set to 0 (fully using the diffuse branch); MLP : weights learned via auxiliary MLP as in UniSDF [ 5 ] .
Fig. 6: Qualitative results of the proposed method under different configurations: (1) Baseline; (2) Baseline + RD (reflection direction for vanilla MLP input); (3) Baseline + RD + MS (microfacet sampling); (4) Full model: baseline + RD + MS + DC (detection-based color blending).
Fig. 7: Qualitative comparison between the MLP-learned and the proposed detection-guided color blending methods on the DTU dataset.
Fig. 8: Qualitative comparison between using view direction and reflective direction as input to the vanilla MLP of the color network.
Fig. 9: Ablation of specular blending weights on the Shiny Blender dataset. Columns: “Reference Image and Normal”;“All Ones” (weights 1, specular branch only); “All Zeros” (weights 0, diffuse branch only); “Stable” (StableDelight detector); “MLP” (learned weights as in UniSDF). For each object, the first row shows the blending weight map, the second row shows the reconstructed normal map.
Fig. 10: Ablation result on diffuse images, showcasing reconstruction of reflective surfaces.
MS
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
×
0.95
0.62
0.32
0.51
0.92
0.58
0.52
1.37
1.01
0.51
0.50
0.69
0.35
0.43
0.39
0.65
✓(wo MNCL)
0.82
0.67
0.38
0.50
0.83
0.63
0.60
1.36
0.96
0.53
0.50
0.67
0.38
0.44
0.40
0.65
✓(w MNCL)
0.53
0.64
0.31
0.44
0.88
0.62
0.56
1.34
1.00
0.52
0.48
0.66
0.33
0.39
0.40
0.607
TABLE VII: Impact of the microfacet normal consistency loss (MNCL) on the DTU dataset (Chamfer Distance (mm) ↓ ). We ablate MNCL while keeping MS, RD, and DC enabled. Red denotes the best results.
Method
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
OpenMVS [ 68 ]
0.53
0.87
0.34
0.38
1.12
1.01
0.65
1.48
1.10
0.72
0.51
0.93
0.35
0.48
0.51
0.73
Ours
0.53
0.64
0.31
0.44
0.88
0.62
0.56
1.34
1.00
0.52
0.48
0.66
0.33
0.39
0.40
0.61
TABLE VIII: Comparison between Dense Initialization and Final Reconstruction Results on DTU. All metrics are reported in Chamfer Distance (mm) ↓ (lower is better). Red denotes the best results.
Fig. 11: Qualitative comparison between OpenMVS [ 68 ] and ours on the scan 55 and scan 114 from the DTU dataset.
GI
MSS
DI
24
37
40
55
63
65
69
83
97
105
106
110
114
118
122
Mean
(a)
Sparse
cur+8
×
0.80
0.69
0.64
1.13
0.55
0.64
0.61
0.50
1.15
0.59
0.59
1.34
0.83
0.59
1.23
0.79
(b)
Sparse
cur+4
✓
1.26
0.71
0.89
0.51
1.37
0.99
0.65
1.23
1.25
0.50
0.56
0.97
0.43
0.48
0.41
0.81
(c)
Sparse
×
×
0.60
0.73
0.52
0.51
1.23
0.96
0.53
0.92
1.17
0.51
0.54
0.70
0.36
0.39
0.37
0.67
(d)
Sparse
cur+4
×
0.67
0.64
0.50
0.50
1.19
0.69
0.58
0.87
1.23
0.50
0.48
0.69
0.35
0.45
0.38
0.65
(e)
Dense
cur+8
×
0.48
0.61
0.35
0.46
0.88
0.64
0.55
1.34
1.03
0.57
0.52
0.69
0.37
0.39
0.40
0.62
(f)
Dense
cur+4
✓
0.65
0.64
0.41
0.50
1.02
0.95
0.65
1.53
1.10
0.52
0.57
0.93
0.41
0.50
0.44
0.72
TABLE IX: Ablation Study on Geometry Initialization (GI), Microfacet Sampling Scale (MSS) and Diffuse Images (DI). All metrics are reported in Chamfer Distance (mm) ↓ (lower is better). Red and orange denote the best and second-best per column. “cur+4” denotes a scale that is 4 levels finer than the current level, and “cur+8” denotes a scale that is 8 levels finer than the current level (i.e., the finest granularity level in our setting).
Fig. 12: Comparison of reconstruction results using different initialization strategies: (a) dense point cloud initialization from OpenMVS, and (b) sparse point cloud initialization from COLMAP.
Neural surface reconstruction has emerged as a powerful paradigm for recovering high-quality 3D surfaces from multi-view images. However, recovering accurate geometry solely from RGB images remains challenging due to uncertainties arising from textureless regions, occlusions, and inherent scene ambiguities. Existing methods often overlook such uncertainties, leading to inaccurate estimates of the signed distance function (SDF). We introduce NeuDonatello, a novel framework that models and leverages SDF uncertainty to improve surface reconstruction. Central to our approach is to model spatially varying uncertainty using a Monte Carlo sampling strategy. Using this uncertainty, we develop an adaptive regularization that selectively strengthens geometric constraints where RGB supervision is unreliable, avoiding incorrect surface reconstruction. We further introduce an uncertainty-aware scale parameter for the SDF-to-density conversion. Conditioned on uncertainty, this design enables more accurate modeling of spatially varying densities. Extensive experiments demonstrate that NeuDonatello achieves state-of-the-art reconstruction accuracy, with robust performance across diverse scenes using only posed RGB images.
Alvin Jinsung Choi, Wanhee Kim, Taeyun Kim +3
Department of Computer Science The University of Texas at Austin Texas, USA · School of Electrical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea · Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon, Republic of Korea +2
Neural implicit surface reconstruction with signed distance function has made significant progress, but recovering fine details such as thin structures and complex geometries remains challenging due to unreliable or noisy geometric priors. Existing approaches rely on implicit uncertainty that arises during optimization to filter these priors, which is indirect and inefficient, and masking supervision in high-uncertainty regions further leads to under-constrained optimization. To address these issues, we propose GPU-SDF, a neural implicit framework for indoor surface reconstruction that leverages geometric prior uncertainty and complementary constraints. We introduce a self-supervised module that explicitly estimates prior uncertainty without auxiliary networks. Based on this estimation, we design an uncertainty-guided loss that modulates prior influence rather than discarding it, thereby retaining weak but informative cues. To address regions with high prior uncertainty, GPU-SDF further incorporates two complementary constraints: an edge distance field that strengthens boundary supervision and a multi-view consistency regularization that enforces geometric coherence. Extensive experiments confirm that GPU-SDF improves the reconstruction of fine details and serves as a plug-and-play enhancement for existing frameworks. Source code will be available at https://github.com/IRMVLab/GPU-SDF
Qiyu Feng, Jiwei Shan, Shing Shin Cheng +1
Department of Automation, Shanghai Jiao Tong University, Shanghai 200240, China. · Department of Mechanical and Automation Engineering and T Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong.
Over the past decade, microfacet-based BRDF models have formed the foundation of real-time rendering pipelines. Despite their widespread use, they often fail to reproduce subtle appearance effects arising from complex light-surface interactions, which have led to the emergence of specialized physics-based models for specific optical phenomena (e.g., diffraction, iridescence, multilayers). Although more accurate, these models lose versatility and lack performance for real-time rendering. Recently introduced, neural models have demonstrated their ability to approximate BRDF reference data coming from measurements, simulations, or even complex shading networks. However, most current neural models require relatively large networks, making them costly for real-time rendering. In this paper, we introduce a hybrid model that combines a GGX-type microfacet model and a neural model to leverage the best features of both representations. The neural component corrects the appearance approximated by the microfacet component, allowing much smaller network than in existing neural models. We show that, at identical memory cost, our model approximates measurements better than state-of-the-art neural models for a low evaluation overhead compared to a microfacet-based model. Furthermore, our hybrid model remains easily editable by artists and benefits from an important sampling scheme, making it attractive for both offline and real-time rendering.
Louis De Oliveira, Anastasia Karpova, Georges Nader +4